kempersc/glam
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

data(person): resolve PPID locations and enrich profiles

Browse source 
- Rename 512 person files from XX-XX-XXX placeholders to proper GeoNames locations
- Update 2,463 profiles with enriched data
- Add 512 new person profiles (AU, international heritage professionals)
- PPID format: ID_{birth-loc}_{decade}_{work-loc}_{custodian}_{NAME}
This commit is contained in:
kempersc 2026-01-09 21:09:28 +01:00
parent eb122e2532
commit 855fff5962
3025 changed files with 61541 additions and 22218 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

149
data/person/ID_XX-XX-XXX_195X_XX-XX-XXX_XXXX_KEVIN-BRADLEY.json → data/person/ID_AU-01-CAN_195X_AU-01-CAN_XXXX_KEVIN-BRADLEY.json
View file

@ -1,11 +1,11 @@
{
"ppid": "ID_XX-XX-XXX_195X_XX-XX-XXX_XXXX_KEVIN-BRADLEY",
"ppid": "ID_AU-01-CAN_195X_AU-01-CAN_XXXX_KEVIN-BRADLEY",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-01-CAN",
"first_date": "195X",
"last_location": "XX-XX-XXX",
"last_location": "AU-01-CAN",
"last_date": "XXXX",
"name_tokens": [
"KEVIN",
@ -14,7 +14,9 @@
"first_date_source": "inferred_birth_decade.primary_value",
"first_date_alternatives": [
"196X"
]
],
"first_location_source": "inferred_birth_settlement",
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "Kevin Bradley",
@ -170,7 +172,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/kevin-bradley-psm-3127a41b_20251214T103753Z.json"
],
"modified_at": "2026-01-09T19:18:15.682586+00:00",
"modified_at": "2026-01-09T19:51:13.413292+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "kevin-bradley-psm-3127a41b",
@ -183,6 +185,17 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_195X_XX-XX-XXX_XXXX_KEVIN-BRADLEY",
"new_ppid": "ID_AU-01-CAN_195X_AU-01-CAN_XXXX_KEVIN-BRADLEY",
"changed_at": "2026-01-09T19:51:13.413290+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -197,7 +210,7 @@
"primary_rationale": "1957 is in 195X, but range extends into 196X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_experience_heuristic",
"inference_chain": [
{
"step": 1,
@ -246,7 +259,129 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 1957 spans decades 195X/196X",
"inferred_at": "2026-01-09T19:18:15.682549+00:00",
"inferred_at": "2026-01-09T19:51:13.399317+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_birth_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_job_location",
"inference_chain": [
{
"step": 1,
"observation": "Earliest job with location found (no education location available)",
"source_field": "profile_data.experience",
"source_value": {
"company": "Gilet Guitars",
"title": "Luthier",
"date_range": "Oct 1980 - Dec 1982 • 2 years and 2 months",
"location": "Sydney"
}
},
{
"step": 2,
"observation": "Earliest job with location found (no education location available)",
"source_field": "profile_data.experience",
"source_value": {
"company": "National Library of Australia",
"title": "Sound Archivist",
"date_range": "Jan 1983 - Dec 1992 • 9 years and 11 months",
"location": "Canberra, Australia"
}
},
{
"step": 3,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australia",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 4,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"First job location represents early life region"
],
"assumption_note": "Job location is weak proxy for birth location; person likely relocated for work",
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:51:13.406724+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_current_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "medium",
"inference_provenance": {
"method": "profile_location",
"inference_chain": [
{
"step": 1,
"observation": "Profile location field found",
"source_field": "profile_data.location",
"source_value": "Canberra, Australian Capital Territory, Australia (AU)"
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australian Capital Territory, Australia (AU)",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"Profile location is up-to-date",
"Profile location represents current residence"
],
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:51:13.413275+00:00",
"inferred_by": "enrich_ppids.py"
}
}

149
data/person/ID_XX-XX-XXX_196X_XX-XX-XXX_XXXX_GIANOULA-BURNS.json → data/person/ID_AU-01-CAN_196X_AU-01-CAN_XXXX_GIANOULA-BURNS.json
View file

@ -1,11 +1,11 @@
{
"ppid": "ID_XX-XX-XXX_196X_XX-XX-XXX_XXXX_GIANOULA-BURNS",
"ppid": "ID_AU-01-CAN_196X_AU-01-CAN_XXXX_GIANOULA-BURNS",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-01-CAN",
"first_date": "196X",
"last_location": "XX-XX-XXX",
"last_location": "AU-01-CAN",
"last_date": "XXXX",
"name_tokens": [
"GIANOULA",
@ -14,7 +14,9 @@
"first_date_source": "inferred_birth_decade.primary_value",
"first_date_alternatives": [
"197X"
]
],
"first_location_source": "inferred_birth_settlement",
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "Gianoula Burns",
@ -131,7 +133,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/gianoula-burns-018272112_20251214T103915Z.json"
],
"modified_at": "2026-01-09T19:18:13.790376+00:00",
"modified_at": "2026-01-09T19:50:56.583015+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "gianoula-burns-018272112",
@ -144,6 +146,17 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_196X_XX-XX-XXX_XXXX_GIANOULA-BURNS",
"new_ppid": "ID_AU-01-CAN_196X_AU-01-CAN_XXXX_GIANOULA-BURNS",
"changed_at": "2026-01-09T19:50:56.583013+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -158,7 +171,7 @@
"primary_rationale": "1968 is in 196X, but range extends into 197X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_education_heuristic",
"inference_chain": [
{
"step": 1,
@ -207,7 +220,129 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 1968 spans decades 196X/197X",
"inferred_at": "2026-01-09T19:18:13.790327+00:00",
"inferred_at": "2026-01-09T19:50:56.573148+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_birth_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_job_location",
"inference_chain": [
{
"step": 1,
"observation": "Earliest job with location found (no education location available)",
"source_field": "profile_data.experience",
"source_value": {
"company": "Country Energy",
"title": "HRD Consultant",
"date_range": "Feb 1997 - Jul 1999 • 2 years and 5 months",
"location": "Queanbeyan"
}
},
{
"step": 2,
"observation": "Earliest job with location found (no education location available)",
"source_field": "profile_data.experience",
"source_value": {
"company": "ANU Enterprise",
"title": "Senior HR Manager",
"date_range": "Aug 1999 - Apr 2000 • 8 months",
"location": "Canberra, Australia"
}
},
{
"step": 3,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australia",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 4,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"First job location represents early life region"
],
"assumption_note": "Job location is weak proxy for birth location; person likely relocated for work",
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:50:56.578215+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_current_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "medium",
"inference_provenance": {
"method": "profile_location",
"inference_chain": [
{
"step": 1,
"observation": "Profile location field found",
"source_field": "profile_data.location",
"source_value": "Canberra, Australian Capital Territory, Australia (AU)"
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australian Capital Territory, Australia (AU)",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"Profile location is up-to-date",
"Profile location represents current residence"
],
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:50:56.583005+00:00",
"inferred_by": "enrich_ppids.py"
}
}

149
data/person/ID_XX-XX-XXX_196X_XX-XX-XXX_XXXX_VERA-DUNN.json → data/person/ID_AU-01-CAN_196X_AU-01-CAN_XXXX_VERA-DUNN.json
View file

@ -1,11 +1,11 @@
{
"ppid": "ID_XX-XX-XXX_196X_XX-XX-XXX_XXXX_VERA-DUNN",
"ppid": "ID_AU-01-CAN_196X_AU-01-CAN_XXXX_VERA-DUNN",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-01-CAN",
"first_date": "196X",
"last_location": "XX-XX-XXX",
"last_location": "AU-01-CAN",
"last_date": "XXXX",
"name_tokens": [
"VERA",
@ -14,7 +14,9 @@
"first_date_source": "inferred_birth_decade.primary_value",
"first_date_alternatives": [
"197X"
]
],
"first_location_source": "inferred_birth_settlement",
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "Vera Dunn",
@ -135,7 +137,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/vera-dunn-5575a127_20251214T103803Z.json"
],
"modified_at": "2026-01-09T19:18:13.075254+00:00",
"modified_at": "2026-01-09T19:50:51.037273+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "vera-dunn-5575a127",
@ -148,6 +150,17 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_196X_XX-XX-XXX_XXXX_VERA-DUNN",
"new_ppid": "ID_AU-01-CAN_196X_AU-01-CAN_XXXX_VERA-DUNN",
"changed_at": "2026-01-09T19:50:51.037270+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -162,7 +175,7 @@
"primary_rationale": "1969 is in 196X, but range extends into 197X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_experience_heuristic",
"inference_chain": [
{
"step": 1,
@ -211,7 +224,129 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 1969 spans decades 196X/197X",
"inferred_at": "2026-01-09T19:18:13.075227+00:00",
"inferred_at": "2026-01-09T19:50:51.023125+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_birth_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_job_location",
"inference_chain": [
{
"step": 1,
"observation": "Earliest job with location found (no education location available)",
"source_field": "profile_data.experience",
"source_value": {
"company": "National Library of Australia",
"title": "Collection Development Librarian, Overseas Collections",
"date_range": "Nov 2002 - Jan 2014 • 11 years and 2 months",
"location": "Pacific specialist"
}
},
{
"step": 2,
"observation": "Earliest job with location found (no education location available)",
"source_field": "profile_data.experience",
"source_value": {
"company": "National Library of Australia",
"title": "Contributor Liaison Officer (APS6), Australian Newspaper Digitisation Program",
"date_range": "Feb 2014 - Aug 2014 • 6 months",
"location": "Canberra, Australia"
}
},
{
"step": 3,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australia",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 4,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"First job location represents early life region"
],
"assumption_note": "Job location is weak proxy for birth location; person likely relocated for work",
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:50:51.028647+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_current_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "medium",
"inference_provenance": {
"method": "profile_location",
"inference_chain": [
{
"step": 1,
"observation": "Profile location field found",
"source_field": "profile_data.location",
"source_value": "Canberra, Australian Capital Territory, Australia (AU)"
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australian Capital Territory, Australia (AU)",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"Profile location is up-to-date",
"Profile location represents current residence"
],
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:50:51.037254+00:00",
"inferred_by": "enrich_ppids.py"
}
}

138
data/person/ID_XX-XX-XXX_197X_XX-XX-XXX_XXXX_CATHERINE-ALDERSEY.json → data/person/ID_AU-01-CAN_197X_AU-01-CAN_XXXX_CATHERINE-ALDERSEY.json
View file

@ -1,17 +1,19 @@
{
"ppid": "ID_XX-XX-XXX_197X_XX-XX-XXX_XXXX_CATHERINE-ALDERSEY",
"ppid": "ID_AU-01-CAN_197X_AU-01-CAN_XXXX_CATHERINE-ALDERSEY",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-01-CAN",
"first_date": "197X",
"last_location": "XX-XX-XXX",
"last_location": "AU-01-CAN",
"last_date": "XXXX",
"name_tokens": [
"CATHERINE",
"ALDERSEY"
],
"first_date_source": "inferred_birth_decade"
"first_date_source": "inferred_birth_decade",
"first_location_source": "inferred_birth_settlement",
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "Catherine Aldersey",
@ -113,7 +115,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/catherine-aldersey-a0b56914_20251214T103937Z.json"
],
"modified_at": "2026-01-09T19:18:14.008164+00:00",
"modified_at": "2026-01-09T19:50:58.061567+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "catherine-aldersey-a0b56914",
@ -126,6 +128,17 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_197X_XX-XX-XXX_XXXX_CATHERINE-ALDERSEY",
"new_ppid": "ID_AU-01-CAN_197X_AU-01-CAN_XXXX_CATHERINE-ALDERSEY",
"changed_at": "2026-01-09T19:50:58.061564+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -134,7 +147,7 @@
"precision": "decade",
"confidence": "low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_education_heuristic",
"inference_chain": [
{
"step": 1,
@ -175,7 +188,118 @@
"Entry age for education/first job: 18 years (±3)",
"Career records are complete in LinkedIn profile"
],
"inferred_at": "2026-01-09T19:18:14.008118+00:00",
"inferred_at": "2026-01-09T19:50:58.048315+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_birth_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_job_location",
"inference_chain": [
{
"step": 1,
"observation": "Earliest job with location found (no education location available)",
"source_field": "profile_data.experience",
"source_value": {
"company": "National Library of Australia",
"title": "Manuscripts Acquisitions",
"date_range": "Oct 2018 - Nov 2020 • 2 years and 1 month",
"location": "Canberra, Australian Capital Territory, Australia"
}
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australian Capital Territory, Australia",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"First job location represents early life region"
],
"assumption_note": "Job location is weak proxy for birth location; person likely relocated for work",
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:50:58.053584+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_current_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "medium",
"inference_provenance": {
"method": "profile_location",
"inference_chain": [
{
"step": 1,
"observation": "Profile location field found",
"source_field": "profile_data.location",
"source_value": "Canberra, Australian Capital Territory, Australia (AU)"
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australian Capital Territory, Australia (AU)",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"Profile location is up-to-date",
"Profile location represents current residence"
],
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:50:58.061549+00:00",
"inferred_by": "enrich_ppids.py"
}
}

150
data/person/ID_XX-XX-XXX_197X_XX-XX-XXX_XXXX_COLETTE-LILLE.json → data/person/ID_AU-01-CAN_197X_AU-01-CAN_XXXX_COLETTE-LILLE.json
View file

@ -1,11 +1,11 @@
{
"ppid": "ID_XX-XX-XXX_197X_XX-XX-XXX_XXXX_COLETTE-LILLE",
"ppid": "ID_AU-01-CAN_197X_AU-01-CAN_XXXX_COLETTE-LILLE",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-01-CAN",
"first_date": "197X",
"last_location": "XX-XX-XXX",
"last_location": "AU-01-CAN",
"last_date": "XXXX",
"name_tokens": [
"COLETTE",
@ -14,7 +14,9 @@
"first_date_source": "inferred_birth_decade.primary_value",
"first_date_alternatives": [
"196X"
]
],
"first_location_source": "inferred_birth_settlement",
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "Colette van Lille",
@ -107,7 +109,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/colette-van-lille-9132358_20251214T103803Z.json"
],
"modified_at": "2026-01-09T19:18:17.842988+00:00",
"modified_at": "2026-01-09T19:50:48.415993+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "colette-van-lille-9132358",
@ -129,6 +131,17 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_197X_XX-XX-XXX_XXXX_COLETTE-LILLE",
"new_ppid": "ID_AU-01-CAN_197X_AU-01-CAN_XXXX_COLETTE-LILLE",
"changed_at": "2026-01-09T19:50:48.415989+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -143,7 +156,7 @@
"primary_rationale": "1972 is in 197X, but range extends into 196X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_education_heuristic",
"inference_chain": [
{
"step": 1,
@ -192,7 +205,130 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 1972 spans decades 196X/197X",
"inferred_at": "2026-01-09T19:18:17.842888+00:00",
"inferred_at": "2026-01-09T19:50:48.281478+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_birth_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "low",
"inference_provenance": {
"method": "earliest_education_location",
"inference_chain": [
{
"step": 1,
"observation": "Earliest education institution identified",
"source_field": "profile_data.education",
"source_value": {
"institution": "The Australian National University",
"date_range": "1990 - 1995 • 5 years",
"degree": ""
}
},
{
"step": 2,
"lookup": "Institution location mapping",
"mapping_source": "DUTCH_UNI_LOCATIONS dictionary",
"mapping_key": "The Australian National University",
"mapping_result": "Canberra, Australia"
},
{
"step": 3,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australia",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 4,
"formatting": "CC-RR-PPP generation",
"components": {
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN"
},
"result": "AU-01-CAN"
}
],
"assumptions": [
"Student attended school near birth/family residence",
"Institution location is representative of early life location"
],
"assumption_note": "University location used as proxy for birth settlement; student may have relocated for education",
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:50:48.410700+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_current_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "medium",
"inference_provenance": {
"method": "profile_location",
"inference_chain": [
{
"step": 1,
"observation": "Profile location field found",
"source_field": "profile_data.location",
"source_value": "Canberra, Australian Capital Territory, Australia (AU)"
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australian Capital Territory, Australia (AU)",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"Profile location is up-to-date",
"Profile location represents current residence"
],
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:50:48.415973+00:00",
"inferred_by": "enrich_ppids.py"
}
}

138
data/person/ID_XX-XX-XXX_197X_XX-XX-XXX_XXXX_CONOR-MCCARTHY.json → data/person/ID_AU-01-CAN_197X_AU-01-CAN_XXXX_CONOR-MCCARTHY.json
View file

@ -1,11 +1,11 @@
{
"ppid": "ID_XX-XX-XXX_197X_XX-XX-XXX_XXXX_CONOR-MCCARTHY",
"ppid": "ID_AU-01-CAN_197X_AU-01-CAN_XXXX_CONOR-MCCARTHY",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-01-CAN",
"first_date": "197X",
"last_location": "XX-XX-XXX",
"last_location": "AU-01-CAN",
"last_date": "XXXX",
"name_tokens": [
"CONOR",
@ -14,7 +14,9 @@
"first_date_source": "inferred_birth_decade.primary_value",
"first_date_alternatives": [
"196X"
]
],
"first_location_source": "inferred_birth_settlement",
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "Conor McCarthy",
@ -142,7 +144,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/conor-mccarthy-23914913_20251214T103930Z.json"
],
"modified_at": "2026-01-09T19:18:15.832961+00:00",
"modified_at": "2026-01-09T19:51:14.523551+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "conor-mccarthy-23914913",
@ -155,6 +157,17 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_197X_XX-XX-XXX_XXXX_CONOR-MCCARTHY",
"new_ppid": "ID_AU-01-CAN_197X_AU-01-CAN_XXXX_CONOR-MCCARTHY",
"changed_at": "2026-01-09T19:51:14.523549+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -169,7 +182,7 @@
"primary_rationale": "1971 is in 197X, but range extends into 196X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_education_heuristic",
"inference_chain": [
{
"step": 1,
@ -218,7 +231,118 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 1971 spans decades 196X/197X",
"inferred_at": "2026-01-09T19:18:15.832912+00:00",
"inferred_at": "2026-01-09T19:51:14.513309+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_birth_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_job_location",
"inference_chain": [
{
"step": 1,
"observation": "Earliest job with location found (no education location available)",
"source_field": "profile_data.experience",
"source_value": {
"company": "National Library of Australia",
"title": "Director Of Philanthropy",
"date_range": "Dec 2019 - Present • 5 years and 11 months",
"location": "Canberra, Australia"
}
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australia",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"First job location represents early life region"
],
"assumption_note": "Job location is weak proxy for birth location; person likely relocated for work",
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:51:14.518295+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_current_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "medium",
"inference_provenance": {
"method": "profile_location",
"inference_chain": [
{
"step": 1,
"observation": "Profile location field found",
"source_field": "profile_data.location",
"source_value": "Canberra, Australian Capital Territory, Australia (AU)"
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australian Capital Territory, Australia (AU)",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"Profile location is up-to-date",
"Profile location represents current residence"
],
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:51:14.523539+00:00",
"inferred_by": "enrich_ppids.py"
}
}

193
data/person/ID_XX-XX-XXX_197X_XX-XX-XXX_XXXX_DAVID-WONG.json → data/person/ID_AU-01-CAN_197X_AU-01-CAN_XXXX_DAVID-WONG.json
View file

@ -1,11 +1,11 @@
{
"ppid": "ID_XX-XX-XXX_197X_XX-XX-XXX_XXXX_DAVID-WONG",
"ppid": "ID_AU-01-CAN_197X_AU-01-CAN_XXXX_DAVID-WONG",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-01-CAN",
"first_date": "197X",
"last_location": "XX-XX-XXX",
"last_location": "AU-01-CAN",
"last_date": "XXXX",
"name_tokens": [
"DAVID",
@ -14,7 +14,9 @@
"first_date_source": "inferred_birth_decade.primary_value",
"first_date_alternatives": [
"198X"
]
],
"first_location_source": "inferred_birth_settlement",
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "David Wong",
@ -153,7 +155,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/davidwong6_20251214T103836Z.json"
],
"modified_at": "2026-01-09T19:18:13.876337+00:00",
"modified_at": "2026-01-09T19:50:56.750253+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "davidwong6",
@ -166,6 +168,17 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_197X_XX-XX-XXX_XXXX_DAVID-WONG",
"new_ppid": "ID_AU-01-CAN_197X_AU-01-CAN_XXXX_DAVID-WONG",
"changed_at": "2026-01-09T19:50:56.750250+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -180,7 +193,7 @@
"primary_rationale": "1977 is in 197X, but range extends into 198X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_experience_heuristic",
"inference_chain": [
{
"step": 1,
@ -229,7 +242,173 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 1977 spans decades 197X/198X",
"inferred_at": "2026-01-09T19:18:13.876301+00:00",
"inferred_at": "2026-01-09T19:50:56.732811+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_birth_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_job_location",
"inference_chain": [
{
"step": 1,
"observation": "Earliest job with location found (no education location available)",
"source_field": "profile_data.experience",
"source_value": {
"company": "ObjectMastery",
"title": "Software Engineer",
"date_range": "Jan 2000 - Jul 2001 • 1 year and 6 months",
"location": "Financial Services"
}
},
{
"step": 2,
"observation": "Earliest job with location found (no education location available)",
"source_field": "profile_data.experience",
"source_value": {
"company": "Department of Defence of Australia",
"title": "E-Business Solutions Developer",
"date_range": "Apr 2002 - Oct 2003 • 1 year and 6 months",
"location": "Corporate Services and Infrastructure Group"
}
},
{
"step": 3,
"observation": "Earliest job with location found (no education location available)",
"source_field": "profile_data.experience",
"source_value": {
"company": "National Library of Australia",
"title": "Applications Developer",
"date_range": "Nov 2003 - Aug 2005 • 1 year and 9 months",
"location": "Java and XML developer"
}
},
{
"step": 4,
"observation": "Earliest job with location found (no education location available)",
"source_field": "profile_data.experience",
"source_value": {
"company": "National Library of Australia",
"title": "Team Leader",
"date_range": "Sep 2005 - Sep 2006 • 1 year",
"location": "Web archiving systems"
}
},
{
"step": 5,
"observation": "Earliest job with location found (no education location available)",
"source_field": "profile_data.experience",
"source_value": {
"company": "Department of Foreign Affairs and Trade",
"title": "Senior Applications Developer",
"date_range": "Sep 2006 - Sep 2007 • 1 year",
"location": "IBM WebSphere applications and infrastructure developer"
}
},
{
"step": 6,
"observation": "Earliest job with location found (no education location available)",
"source_field": "profile_data.experience",
"source_value": {
"company": "National Library of Australia",
"title": "Chief Information Officer",
"date_range": "Oct 2015 - Present • 10 years and 1 month",
"location": "Canberra, Australia"
}
},
{
"step": 7,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australia",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 8,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"First job location represents early life region"
],
"assumption_note": "Job location is weak proxy for birth location; person likely relocated for work",
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:50:56.744165+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_current_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "medium",
"inference_provenance": {
"method": "profile_location",
"inference_chain": [
{
"step": 1,
"observation": "Profile location field found",
"source_field": "profile_data.location",
"source_value": "Canberra, Australian Capital Territory, Australia (AU)"
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australian Capital Territory, Australia (AU)",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"Profile location is up-to-date",
"Profile location represents current residence"
],
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:50:56.750234+00:00",
"inferred_by": "enrich_ppids.py"
}
}

138
data/person/ID_XX-XX-XXX_197X_XX-XX-XXX_XXXX_FRANCIS-CRIMMINS.json → data/person/ID_AU-01-CAN_197X_AU-01-CAN_XXXX_FRANCIS-CRIMMINS.json
View file

@ -1,11 +1,11 @@
{
"ppid": "ID_XX-XX-XXX_197X_XX-XX-XXX_XXXX_FRANCIS-CRIMMINS",
"ppid": "ID_AU-01-CAN_197X_AU-01-CAN_XXXX_FRANCIS-CRIMMINS",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-01-CAN",
"first_date": "197X",
"last_location": "XX-XX-XXX",
"last_location": "AU-01-CAN",
"last_date": "XXXX",
"name_tokens": [
"FRANCIS",
@ -14,7 +14,9 @@
"first_date_source": "inferred_birth_decade",
"first_date_alternatives": [
"197X"
]
],
"first_location_source": "inferred_birth_settlement",
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "Francis Crimmins",
@ -143,7 +145,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/franciscrimmins_20251214T103831Z.json"
],
"modified_at": "2026-01-09T19:18:16.776428+00:00",
"modified_at": "2026-01-09T19:50:58.703980+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "franciscrimmins",
@ -165,6 +167,17 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_197X_XX-XX-XXX_XXXX_FRANCIS-CRIMMINS",
"new_ppid": "ID_AU-01-CAN_197X_AU-01-CAN_XXXX_FRANCIS-CRIMMINS",
"changed_at": "2026-01-09T19:50:58.703977+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -173,7 +186,7 @@
"precision": "decade",
"confidence": "low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_education_heuristic",
"inference_chain": [
{
"step": 1,
@ -214,7 +227,118 @@
"Entry age for education/first job: 18 years (±3)",
"Career records are complete in LinkedIn profile"
],
"inferred_at": "2026-01-09T19:18:16.776361+00:00",
"inferred_at": "2026-01-09T19:50:58.684345+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_birth_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_job_location",
"inference_chain": [
{
"step": 1,
"observation": "Earliest job with location found (no education location available)",
"source_field": "profile_data.experience",
"source_value": {
"company": "Funnelback Pty",
"title": "Senior Software Engineer",
"date_range": "Dec 2005 - Jul 2014 • 8 years and 7 months",
"location": "Canberra, Australia"
}
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australia",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"First job location represents early life region"
],
"assumption_note": "Job location is weak proxy for birth location; person likely relocated for work",
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:50:58.690469+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_current_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "medium",
"inference_provenance": {
"method": "profile_location",
"inference_chain": [
{
"step": 1,
"observation": "Profile location field found",
"source_field": "profile_data.location",
"source_value": "Canberra, Australian Capital Territory, Australia (AU)"
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australian Capital Territory, Australia (AU)",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"Profile location is up-to-date",
"Profile location represents current residence"
],
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:50:58.703961+00:00",
"inferred_by": "enrich_ppids.py"
}
}

150
data/person/ID_XX-XX-XXX_197X_XX-XX-XXX_XXXX_HEATHER-CLARK.json → data/person/ID_AU-01-CAN_197X_AU-01-CAN_XXXX_HEATHER-CLARK.json
View file

@ -1,17 +1,19 @@
{
"ppid": "ID_XX-XX-XXX_197X_XX-XX-XXX_XXXX_HEATHER-CLARK",
"ppid": "ID_AU-01-CAN_197X_AU-01-CAN_XXXX_HEATHER-CLARK",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-01-CAN",
"first_date": "197X",
"last_location": "XX-XX-XXX",
"last_location": "AU-01-CAN",
"last_date": "XXXX",
"name_tokens": [
"HEATHER",
"CLARK"
],
"first_date_source": "inferred_birth_decade"
"first_date_source": "inferred_birth_decade",
"first_location_source": "inferred_birth_settlement",
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "Heather Clark",
@ -133,7 +135,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/heather-clark-b9361998_20251214T103915Z.json"
],
"modified_at": "2026-01-09T19:18:13.147399+00:00",
"modified_at": "2026-01-09T19:50:52.961348+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "heather-clark-b9361998",
@ -146,6 +148,17 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_197X_XX-XX-XXX_XXXX_HEATHER-CLARK",
"new_ppid": "ID_AU-01-CAN_197X_AU-01-CAN_XXXX_HEATHER-CLARK",
"changed_at": "2026-01-09T19:50:52.961346+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -154,7 +167,7 @@
"precision": "decade",
"confidence": "low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_education_heuristic",
"inference_chain": [
{
"step": 1,
@ -195,7 +208,130 @@
"Entry age for education/first job: 18 years (±3)",
"Career records are complete in LinkedIn profile"
],
"inferred_at": "2026-01-09T19:18:13.147342+00:00",
"inferred_at": "2026-01-09T19:50:52.951190+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_birth_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "low",
"inference_provenance": {
"method": "earliest_education_location",
"inference_chain": [
{
"step": 1,
"observation": "Earliest education institution identified",
"source_field": "profile_data.education",
"source_value": {
"institution": "The Australian National University",
"date_range": "1993 - 1996 • 3 years",
"degree": "Bachelor's degree, Economics"
}
},
{
"step": 2,
"lookup": "Institution location mapping",
"mapping_source": "DUTCH_UNI_LOCATIONS dictionary",
"mapping_key": "The Australian National University",
"mapping_result": "Canberra, Australia"
},
{
"step": 3,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australia",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 4,
"formatting": "CC-RR-PPP generation",
"components": {
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN"
},
"result": "AU-01-CAN"
}
],
"assumptions": [
"Student attended school near birth/family residence",
"Institution location is representative of early life location"
],
"assumption_note": "University location used as proxy for birth settlement; student may have relocated for education",
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:50:52.956331+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_current_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "medium",
"inference_provenance": {
"method": "profile_location",
"inference_chain": [
{
"step": 1,
"observation": "Profile location field found",
"source_field": "profile_data.location",
"source_value": "Canberra, Australian Capital Territory, Australia (AU)"
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australian Capital Territory, Australia (AU)",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"Profile location is up-to-date",
"Profile location represents current residence"
],
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:50:52.961336+00:00",
"inferred_by": "enrich_ppids.py"
}
}

149
data/person/ID_XX-XX-XXX_197X_XX-XX-XXX_XXXX_LIBBY-CASS.json → data/person/ID_AU-01-CAN_197X_AU-01-CAN_XXXX_LIBBY-CASS.json
View file

@ -1,11 +1,11 @@
{
"ppid": "ID_XX-XX-XXX_197X_XX-XX-XXX_XXXX_LIBBY-CASS",
"ppid": "ID_AU-01-CAN_197X_AU-01-CAN_XXXX_LIBBY-CASS",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-01-CAN",
"first_date": "197X",
"last_location": "XX-XX-XXX",
"last_location": "AU-01-CAN",
"last_date": "XXXX",
"name_tokens": [
"LIBBY",
@ -14,7 +14,9 @@
"first_date_source": "inferred_birth_decade.primary_value",
"first_date_alternatives": [
"198X"
]
],
"first_location_source": "inferred_birth_settlement",
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "Libby Cass",
@ -140,7 +142,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/libby-cass-88350521_20251214T103851Z.json"
],
"modified_at": "2026-01-09T19:18:15.306770+00:00",
"modified_at": "2026-01-09T19:51:08.497786+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "libby-cass-88350521",
@ -153,6 +155,17 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_197X_XX-XX-XXX_XXXX_LIBBY-CASS",
"new_ppid": "ID_AU-01-CAN_197X_AU-01-CAN_XXXX_LIBBY-CASS",
"changed_at": "2026-01-09T19:51:08.497783+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -167,7 +180,7 @@
"primary_rationale": "1975 is in 197X, but range extends into 198X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_experience_heuristic",
"inference_chain": [
{
"step": 1,
@ -216,7 +229,129 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 1975 spans decades 197X/198X",
"inferred_at": "2026-01-09T19:18:15.306745+00:00",
"inferred_at": "2026-01-09T19:51:08.443484+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_birth_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_job_location",
"inference_chain": [
{
"step": 1,
"observation": "Earliest job with location found (no education location available)",
"source_field": "profile_data.experience",
"source_value": {
"company": "Migration Review Tribunal & Refugee Review Tribunal",
"title": "Library Manager",
"date_range": "Jan 1998 - Jan 2001 • 3 years",
"location": "Sydney"
}
},
{
"step": 2,
"observation": "Earliest job with location found (no education location available)",
"source_field": "profile_data.experience",
"source_value": {
"company": "Council of Australian University Librarians",
"title": "Communications And Policy Officer",
"date_range": "Mar 2013 - Feb 2014 • 11 months",
"location": "Canberra, Australia"
}
},
{
"step": 3,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australia",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 4,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"First job location represents early life region"
],
"assumption_note": "Job location is weak proxy for birth location; person likely relocated for work",
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:51:08.483910+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_current_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "medium",
"inference_provenance": {
"method": "profile_location",
"inference_chain": [
{
"step": 1,
"observation": "Profile location field found",
"source_field": "profile_data.location",
"source_value": "Canberra, Australian Capital Territory, Australia (AU)"
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australian Capital Territory, Australia (AU)",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"Profile location is up-to-date",
"Profile location represents current residence"
],
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:51:08.497763+00:00",
"inferred_by": "enrich_ppids.py"
}
}

166
data/person/ID_XX-XX-XXX_197X_XX-XX-XXX_XXXX_MARTIN-THOMAS.json → data/person/ID_AU-01-CAN_197X_AU-01-CAN_XXXX_MARTIN-THOMAS.json
View file

@ -1,11 +1,11 @@
{
"ppid": "ID_XX-XX-XXX_197X_XX-XX-XXX_XXXX_MARTIN-THOMAS",
"ppid": "ID_AU-01-CAN_197X_AU-01-CAN_XXXX_MARTIN-THOMAS",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-01-CAN",
"first_date": "197X",
"last_location": "XX-XX-XXX",
"last_location": "AU-01-CAN",
"last_date": "XXXX",
"name_tokens": [
"MARTIN",
@ -14,7 +14,9 @@
"first_date_source": "inferred_birth_decade.primary_value",
"first_date_alternatives": [
"196X"
]
],
"first_location_source": "inferred_birth_settlement",
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "Martin Thomas",
@ -146,8 +148,10 @@
],
"enrichment_metadata": {
"birth_date_search": {
"attempted": false,
"notes": "Not yet searched - requires manual enrichment"
"attempted": true,
"searched_on": "2025-01-10T00:27:00Z",
"result": "not_found",
"notes": "Exa search found a different Martin Thomas (born 1964 UK). The Australian ANU professor's birth date not found. Search query: \"Martin Thomas\" ANU professor history born birthday biography"
}
},
"provenance": {
@ -156,7 +160,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/martin-thomas-3a9857276_20251214T103906Z.json"
],
"modified_at": "2026-01-09T19:18:13.463291+00:00",
"modified_at": "2026-01-09T19:50:54.505339+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "martin-thomas-3a9857276",
@ -169,6 +173,17 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_197X_XX-XX-XXX_XXXX_MARTIN-THOMAS",
"new_ppid": "ID_AU-01-CAN_197X_AU-01-CAN_XXXX_MARTIN-THOMAS",
"changed_at": "2026-01-09T19:50:54.505337+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -183,7 +198,7 @@
"primary_rationale": "1971 is in 197X, but range extends into 196X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_education_heuristic",
"inference_chain": [
{
"step": 1,
@ -232,7 +247,140 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 1971 spans decades 196X/197X",
"inferred_at": "2026-01-09T19:18:13.463241+00:00",
"inferred_at": "2026-01-09T19:50:54.476813+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_birth_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_job_location",
"inference_chain": [
{
"step": 1,
"observation": "Earliest job with location found (no education location available)",
"source_field": "profile_data.experience",
"source_value": {
"company": "Australian Broadcasting Corporation (ABC)",
"title": "Radio Producer",
"date_range": "Jun 1991 - Aug 2008 • 17 years and 2 months",
"location": "Sydney, New South Wales, Australia"
}
},
{
"step": 2,
"observation": "Earliest job with location found (no education location available)",
"source_field": "profile_data.experience",
"source_value": {
"company": "University of Technology Sydney",
"title": "ARC Postdoctoral Fellow",
"date_range": "May 2001 - Apr 2004 • 2 years and 11 months",
"location": "Sydney, New South Wales, Australia"
}
},
{
"step": 3,
"observation": "Earliest job with location found (no education location available)",
"source_field": "profile_data.experience",
"source_value": {
"company": "National Library of Australia",
"title": "Oral History Interviewer",
"date_range": "Jun 2003 - Present • 22 years and 5 months",
"location": "Canberra, Australian Capital Territory, Australia"
}
},
{
"step": 4,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australian Capital Territory, Australia",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 5,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"First job location represents early life region"
],
"assumption_note": "Job location is weak proxy for birth location; person likely relocated for work",
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:50:54.499516+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_current_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "medium",
"inference_provenance": {
"method": "profile_location",
"inference_chain": [
{
"step": 1,
"observation": "Profile location field found",
"source_field": "profile_data.location",
"source_value": "Canberra, Australian Capital Territory, Australia (AU)"
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australian Capital Territory, Australia (AU)",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"Profile location is up-to-date",
"Profile location represents current residence"
],
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:50:54.505325+00:00",
"inferred_by": "enrich_ppids.py"
}
}

138
data/person/ID_XX-XX-XXX_197X_XX-XX-XXX_XXXX_NICOLA-MACKAYSIM.json → data/person/ID_AU-01-CAN_197X_AU-01-CAN_XXXX_NICOLA-MACKAYSIM.json
View file

@ -1,11 +1,11 @@
{
"ppid": "ID_XX-XX-XXX_197X_XX-XX-XXX_XXXX_NICOLA-MACKAYSIM",
"ppid": "ID_AU-01-CAN_197X_AU-01-CAN_XXXX_NICOLA-MACKAYSIM",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-01-CAN",
"first_date": "197X",
"last_location": "XX-XX-XXX",
"last_location": "AU-01-CAN",
"last_date": "XXXX",
"name_tokens": [
"NICOLA",
@ -14,7 +14,9 @@
"first_date_source": "inferred_birth_decade.primary_value",
"first_date_alternatives": [
"196X"
]
],
"first_location_source": "inferred_birth_settlement",
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "Nicola Mackay-Sim",
@ -183,7 +185,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/nicola-mackay-sim-45b4a447_20251214T103949Z.json"
],
"modified_at": "2026-01-09T19:18:15.667052+00:00",
"modified_at": "2026-01-09T19:51:13.387286+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "nicola-mackay-sim-45b4a447",
@ -196,6 +198,17 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_197X_XX-XX-XXX_XXXX_NICOLA-MACKAYSIM",
"new_ppid": "ID_AU-01-CAN_197X_AU-01-CAN_XXXX_NICOLA-MACKAYSIM",
"changed_at": "2026-01-09T19:51:13.387283+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -210,7 +223,7 @@
"primary_rationale": "1972 is in 197X, but range extends into 196X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_experience_heuristic",
"inference_chain": [
{
"step": 1,
@ -259,7 +272,118 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 1972 spans decades 196X/197X",
"inferred_at": "2026-01-09T19:18:15.667013+00:00",
"inferred_at": "2026-01-09T19:51:13.322048+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_birth_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_job_location",
"inference_chain": [
{
"step": 1,
"observation": "Earliest job with location found (no education location available)",
"source_field": "profile_data.experience",
"source_value": {
"company": "National Gallery of Australia",
"title": "Research Assistant, Under A Southern Sun CD Rom Project",
"date_range": "Dec 1995 - Apr 1996 • 4 months",
"location": "Canberra, Australian Capital Territory, Australia"
}
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australian Capital Territory, Australia",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"First job location represents early life region"
],
"assumption_note": "Job location is weak proxy for birth location; person likely relocated for work",
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:51:13.378361+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_current_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "medium",
"inference_provenance": {
"method": "profile_location",
"inference_chain": [
{
"step": 1,
"observation": "Profile location field found",
"source_field": "profile_data.location",
"source_value": "Canberra, Australian Capital Territory, Australia (AU)"
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australian Capital Territory, Australia (AU)",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"Profile location is up-to-date",
"Profile location represents current residence"
],
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:51:13.387261+00:00",
"inferred_by": "enrich_ppids.py"
}
}

150
data/person/ID_XX-XX-XXX_197X_XX-XX-XXX_XXXX_SAOWAPHA-VIRAVONG.json → data/person/ID_AU-01-CAN_197X_AU-01-CAN_XXXX_SAOWAPHA-VIRAVONG.json
View file

@ -1,11 +1,11 @@
{
"ppid": "ID_XX-XX-XXX_197X_XX-XX-XXX_XXXX_SAOWAPHA-VIRAVONG",
"ppid": "ID_AU-01-CAN_197X_AU-01-CAN_XXXX_SAOWAPHA-VIRAVONG",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-01-CAN",
"first_date": "197X",
"last_location": "XX-XX-XXX",
"last_location": "AU-01-CAN",
"last_date": "XXXX",
"name_tokens": [
"SAOWAPHA",
@ -14,7 +14,9 @@
"first_date_source": "inferred_birth_decade",
"first_date_alternatives": [
"198X"
]
],
"first_location_source": "inferred_birth_settlement",
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "Saowapha Viravong",
@ -93,7 +95,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/sophieviravong_20251214T104011Z.json"
],
"modified_at": "2026-01-09T19:18:15.594453+00:00",
"modified_at": "2026-01-09T19:51:12.682975+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "sophieviravong",
@ -106,6 +108,17 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_197X_XX-XX-XXX_XXXX_SAOWAPHA-VIRAVONG",
"new_ppid": "ID_AU-01-CAN_197X_AU-01-CAN_XXXX_SAOWAPHA-VIRAVONG",
"changed_at": "2026-01-09T19:51:12.682972+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -114,7 +127,7 @@
"precision": "decade",
"confidence": "low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_education_heuristic",
"inference_chain": [
{
"step": 1,
@ -155,7 +168,130 @@
"Entry age for education/first job: 22 years (±3)",
"Career records are complete in LinkedIn profile"
],
"inferred_at": "2026-01-09T19:18:15.594420+00:00",
"inferred_at": "2026-01-09T19:51:12.654209+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_birth_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "low",
"inference_provenance": {
"method": "earliest_education_location",
"inference_chain": [
{
"step": 1,
"observation": "Earliest education institution identified",
"source_field": "profile_data.education",
"source_value": {
"institution": "University of Canberra",
"date_range": "1996 - 1997 • 1 year",
"degree": "Grad Dip., Library Information Management"
}
},
{
"step": 2,
"lookup": "Institution location mapping",
"mapping_source": "DUTCH_UNI_LOCATIONS dictionary",
"mapping_key": "University of Canberra",
"mapping_result": "Canberra, Australia"
},
{
"step": 3,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australia",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 4,
"formatting": "CC-RR-PPP generation",
"components": {
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN"
},
"result": "AU-01-CAN"
}
],
"assumptions": [
"Student attended school near birth/family residence",
"Institution location is representative of early life location"
],
"assumption_note": "University location used as proxy for birth settlement; student may have relocated for education",
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:51:12.673600+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_current_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "medium",
"inference_provenance": {
"method": "profile_location",
"inference_chain": [
{
"step": 1,
"observation": "Profile location field found",
"source_field": "profile_data.location",
"source_value": "Canberra, Australian Capital Territory, Australia (AU)"
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australian Capital Territory, Australia (AU)",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"Profile location is up-to-date",
"Profile location represents current residence"
],
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:51:12.682952+00:00",
"inferred_by": "enrich_ppids.py"
}
}

138
data/person/ID_XX-XX-XXX_197X_XX-XX-XXX_XXXX_SIMON-WALL.json → data/person/ID_AU-01-CAN_197X_AU-01-CAN_XXXX_SIMON-WALL.json
View file

@ -1,11 +1,11 @@
{
"ppid": "ID_XX-XX-XXX_197X_XX-XX-XXX_XXXX_SIMON-WALL",
"ppid": "ID_AU-01-CAN_197X_AU-01-CAN_XXXX_SIMON-WALL",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-01-CAN",
"first_date": "197X",
"last_location": "XX-XX-XXX",
"last_location": "AU-01-CAN",
"last_date": "XXXX",
"name_tokens": [
"SIMON",
@ -14,7 +14,9 @@
"first_date_source": "inferred_birth_decade.primary_value",
"first_date_alternatives": [
"196X"
]
],
"first_location_source": "inferred_birth_settlement",
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "Simon Wall",
@ -160,7 +162,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/simonjameswall_20251214T103759Z.json"
],
"modified_at": "2026-01-09T19:18:14.363743+00:00",
"modified_at": "2026-01-09T19:51:01.707156+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "simonjameswall",
@ -173,6 +175,17 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_197X_XX-XX-XXX_XXXX_SIMON-WALL",
"new_ppid": "ID_AU-01-CAN_197X_AU-01-CAN_XXXX_SIMON-WALL",
"changed_at": "2026-01-09T19:51:01.707154+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -187,7 +200,7 @@
"primary_rationale": "1974 is in 197X, but range extends into 196X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_experience_heuristic",
"inference_chain": [
{
"step": 1,
@ -236,7 +249,118 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 1974 spans decades 196X/197X",
"inferred_at": "2026-01-09T19:18:14.363714+00:00",
"inferred_at": "2026-01-09T19:51:01.659791+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_birth_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_job_location",
"inference_chain": [
{
"step": 1,
"observation": "Earliest job with location found (no education location available)",
"source_field": "profile_data.experience",
"source_value": {
"company": "Australian Bureau of Statistics",
"title": "Director (Metadata Infrastructure)",
"date_range": "Jan 2012 - Aug 2016 • 4 years and 7 months",
"location": "Canberra, Australia"
}
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australia",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"First job location represents early life region"
],
"assumption_note": "Job location is weak proxy for birth location; person likely relocated for work",
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:51:01.701628+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_current_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "medium",
"inference_provenance": {
"method": "profile_location",
"inference_chain": [
{
"step": 1,
"observation": "Profile location field found",
"source_field": "profile_data.location",
"source_value": "Canberra, Australian Capital Territory, Australia (AU)"
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australian Capital Territory, Australia (AU)",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"Profile location is up-to-date",
"Profile location represents current residence"
],
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:51:01.707141+00:00",
"inferred_by": "enrich_ppids.py"
}
}

150
data/person/ID_XX-XX-XXX_197X_XX-XX-XXX_XXXX_THERDPUN-KLINJUN.json → data/person/ID_AU-01-CAN_197X_AU-01-CAN_XXXX_THERDPUN-KLINJUN.json
View file

@ -1,11 +1,11 @@
{
"ppid": "ID_XX-XX-XXX_197X_XX-XX-XXX_XXXX_THERDPUN-KLINJUN",
"ppid": "ID_AU-01-CAN_197X_AU-01-CAN_XXXX_THERDPUN-KLINJUN",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-01-CAN",
"first_date": "197X",
"last_location": "XX-XX-XXX",
"last_location": "AU-01-CAN",
"last_date": "XXXX",
"name_tokens": [
"THERDPUN",
@ -14,7 +14,9 @@
"first_date_source": "inferred_birth_decade",
"first_date_alternatives": [
"197X"
]
],
"first_location_source": "inferred_birth_settlement",
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "Therdpun Klinjun",
@ -223,7 +225,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/tklinjun_20251214T103754Z.json"
],
"modified_at": "2026-01-09T19:18:14.136631+00:00",
"modified_at": "2026-01-09T19:51:21.947891+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "tklinjun",
@ -245,6 +247,17 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_197X_XX-XX-XXX_XXXX_THERDPUN-KLINJUN",
"new_ppid": "ID_AU-01-CAN_197X_AU-01-CAN_XXXX_THERDPUN-KLINJUN",
"changed_at": "2026-01-09T19:51:21.947889+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -253,7 +266,7 @@
"precision": "decade",
"confidence": "low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_education_heuristic",
"inference_chain": [
{
"step": 1,
@ -294,7 +307,130 @@
"Entry age for education/first job: 22 years (±3)",
"Career records are complete in LinkedIn profile"
],
"inferred_at": "2026-01-09T19:18:14.136533+00:00",
"inferred_at": "2026-01-09T19:51:21.937671+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_birth_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "low",
"inference_provenance": {
"method": "earliest_education_location",
"inference_chain": [
{
"step": 1,
"observation": "Earliest education institution identified",
"source_field": "profile_data.education",
"source_value": {
"institution": "University of Canberra",
"date_range": "2006 - 2008 • 2 years",
"degree": "Graduate Diploma in Design and Technology, Landscape Architect"
}
},
{
"step": 2,
"lookup": "Institution location mapping",
"mapping_source": "DUTCH_UNI_LOCATIONS dictionary",
"mapping_key": "University of Canberra",
"mapping_result": "Canberra, Australia"
},
{
"step": 3,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australia",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 4,
"formatting": "CC-RR-PPP generation",
"components": {
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN"
},
"result": "AU-01-CAN"
}
],
"assumptions": [
"Student attended school near birth/family residence",
"Institution location is representative of early life location"
],
"assumption_note": "University location used as proxy for birth settlement; student may have relocated for education",
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:51:21.942893+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_current_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "medium",
"inference_provenance": {
"method": "profile_location",
"inference_chain": [
{
"step": 1,
"observation": "Profile location field found",
"source_field": "profile_data.location",
"source_value": "Canberra, Australian Capital Territory, Australia (AU)"
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australian Capital Territory, Australia (AU)",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"Profile location is up-to-date",
"Profile location represents current residence"
],
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:51:21.947879+00:00",
"inferred_by": "enrich_ppids.py"
}
}

160
data/person/ID_XX-XX-XXX_197X_XX-XX-XXX_XXXX_RAMDAH-RADJAB.json → data/person/ID_AU-01-CAN_197X_ID-17-PRA_XXXX_RAMDAH-RADJAB.json
View file

@ -1,17 +1,19 @@
{
"ppid": "ID_XX-XX-XXX_197X_XX-XX-XXX_XXXX_RAMDAH-RADJAB",
"ppid": "ID_AU-01-CAN_197X_ID-17-PRA_XXXX_RAMDAH-RADJAB",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-01-CAN",
"first_date": "197X",
"last_location": "XX-XX-XXX",
"last_location": "ID-17-PRA",
"last_date": "XXXX",
"name_tokens": [
"RAMDAH",
"RADJAB"
],
"first_date_source": "inferred_birth_decade"
"first_date_source": "inferred_birth_decade",
"first_location_source": "inferred_birth_settlement",
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "Ramdah Radjab",
@ -134,7 +136,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/ramdah-radjab-23258a175_20251214T111934Z.json"
],
"modified_at": "2026-01-09T19:18:12.596253+00:00",
"modified_at": "2026-01-09T19:50:48.632124+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "ramdah-radjab-23258a175",
@ -147,6 +149,17 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_197X_XX-XX-XXX_XXXX_RAMDAH-RADJAB",
"new_ppid": "ID_AU-01-CAN_197X_ID-17-PRA_XXXX_RAMDAH-RADJAB",
"changed_at": "2026-01-09T19:50:48.632120+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -155,7 +168,7 @@
"precision": "decade",
"confidence": "low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_education_heuristic",
"inference_chain": [
{
"step": 1,
@ -196,7 +209,140 @@
"Entry age for education/first job: 18 years (±3)",
"Career records are complete in LinkedIn profile"
],
"inferred_at": "2026-01-09T19:18:12.596170+00:00",
"inferred_at": "2026-01-09T19:50:48.517998+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_birth_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "low",
"inference_provenance": {
"method": "earliest_education_location",
"inference_chain": [
{
"step": 1,
"observation": "Earliest education institution identified",
"source_field": "profile_data.education",
"source_value": {
"institution": "University of Canberra",
"date_range": "2006 - 2008 • 2 years",
"degree": "Master of Educational Leadership, Eucational Leadership, Post Graduate"
}
},
{
"step": 2,
"lookup": "Institution location mapping",
"mapping_source": "DUTCH_UNI_LOCATIONS dictionary",
"mapping_key": "University of Canberra",
"mapping_result": "Canberra, Australia"
},
{
"step": 3,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australia",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 4,
"formatting": "CC-RR-PPP generation",
"components": {
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN"
},
"result": "AU-01-CAN"
}
],
"assumptions": [
"Student attended school near birth/family residence",
"Institution location is representative of early life location"
],
"assumption_note": "University location used as proxy for birth settlement; student may have relocated for education",
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:50:48.524195+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_current_settlement": {
"value": "Praya",
"formatted": "ID-17-PRA",
"country_code": "ID",
"region_code": "17",
"settlement_code": "PRA",
"confidence": "medium",
"inference_provenance": {
"method": "current_job_location",
"inference_chain": [
{
"step": 1,
"observation": "Profile location field found",
"source_field": "profile_data.location",
"source_value": "West Nusa Tenggara, Indonesia (ID)"
},
{
"step": 2,
"observation": "Current job with location found",
"source_field": "profile_data.experience",
"source_value": {
"company": "Food and Beverage Service Department",
"title": "Head Of Department",
"location": "Praya, West Nusa Tenggara, Indonesia"
}
},
{
"step": 3,
"geocoding": "GeoNames resolution",
"query": "Praya, West Nusa Tenggara, Indonesia",
"result": {
"geonames_id": 1630662,
"geonames_name": "Praya",
"admin1_code": "17",
"admin1_name": "West Nusa Tenggara",
"feature_code": "PPLA3",
"latitude": -8.70536,
"longitude": 116.27036
}
},
{
"step": 4,
"formatting": "CC-RR-PPP generation",
"result": "ID-17-PRA"
}
],
"assumptions": [
"Current job location represents residence area",
"Person works near where they live"
],
"geonames_data": {
"geonames_id": 1630662,
"geonames_name": "Praya",
"admin1_code": "17",
"admin1_name": "West Nusa Tenggara",
"feature_code": "PPLA3",
"latitude": -8.70536,
"longitude": 116.27036
},
"inferred_at": "2026-01-09T19:50:48.632082+00:00",
"inferred_by": "enrich_ppids.py"
}
}

171
data/person/ID_XX-XX-XXX_198X_XX-XX-XXX_XXXX_ADITYA-BURRA.json → data/person/ID_AU-01-CAN_198X_AU-01-CAN_XXXX_ADITYA-BURRA.json
View file

@ -1,11 +1,11 @@
{
"ppid": "ID_XX-XX-XXX_198X_XX-XX-XXX_XXXX_ADITYA-BURRA",
"ppid": "ID_AU-01-CAN_198X_AU-01-CAN_XXXX_ADITYA-BURRA",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-01-CAN",
"first_date": "198X",
"last_location": "XX-XX-XXX",
"last_location": "AU-01-CAN",
"last_date": "XXXX",
"name_tokens": [
"ADITYA",
@ -14,7 +14,9 @@
"first_date_source": "inferred_birth_decade.primary_value",
"first_date_alternatives": [
"199X"
]
],
"first_location_source": "inferred_birth_settlement",
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "Aditya Burra",
@ -106,7 +108,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/aditya-burra-14098052_20251214T103831Z.json"
],
"modified_at": "2026-01-09T19:18:13.145525+00:00",
"modified_at": "2026-01-09T19:50:52.947590+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "aditya-burra-14098052",
@ -119,6 +121,17 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_198X_XX-XX-XXX_XXXX_ADITYA-BURRA",
"new_ppid": "ID_AU-01-CAN_198X_AU-01-CAN_XXXX_ADITYA-BURRA",
"changed_at": "2026-01-09T19:50:52.947587+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -133,7 +146,7 @@
"primary_rationale": "1987 is in 198X, but range extends into 199X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_experience_heuristic",
"inference_chain": [
{
"step": 1,
@ -182,7 +195,151 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 1987 spans decades 198X/199X",
"inferred_at": "2026-01-09T19:18:13.145504+00:00",
"inferred_at": "2026-01-09T19:50:52.796518+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_birth_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_job_location",
"inference_chain": [
{
"step": 1,
"observation": "Earliest job with location found (no education location available)",
"source_field": "profile_data.experience",
"source_value": {
"company": "British Gas",
"title": "Senior Java Developer",
"date_range": "Oct 2010 - May 2013 • 2 years and 7 months",
"location": "Staines-Upon-Thames, United Kingdom"
}
},
{
"step": 2,
"observation": "Earliest job with location found (no education location available)",
"source_field": "profile_data.experience",
"source_value": {
"company": "Cognizant Technology Solutions",
"title": "Associate Projects",
"date_range": "Oct 2010 - Sep 2016 • 5 years and 11 months",
"location": "Staines-Upon-Thames, United Kingdom"
}
},
{
"step": 3,
"observation": "Earliest job with location found (no education location available)",
"source_field": "profile_data.experience",
"source_value": {
"company": "British Gas",
"title": "Lead Developer",
"date_range": "Jun 2013 - Sep 2016 • 3 years and 3 months",
"location": "Staines-Upon-Thames, United Kingdom"
}
},
{
"step": 4,
"observation": "Earliest job with location found (no education location available)",
"source_field": "profile_data.experience",
"source_value": {
"company": "National Library of Australia",
"title": "Java Consultant",
"date_range": "Nov 2016 - Present • 9 years",
"location": "Canberra, Australia"
}
},
{
"step": 5,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australia",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 6,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"First job location represents early life region"
],
"assumption_note": "Job location is weak proxy for birth location; person likely relocated for work",
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:50:52.935690+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_current_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "medium",
"inference_provenance": {
"method": "profile_location",
"inference_chain": [
{
"step": 1,
"observation": "Profile location field found",
"source_field": "profile_data.location",
"source_value": "Canberra, Australian Capital Territory, Australia (AU)"
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australian Capital Territory, Australia (AU)",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"Profile location is up-to-date",
"Profile location represents current residence"
],
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:50:52.947567+00:00",
"inferred_by": "enrich_ppids.py"
}
}

138
data/person/ID_XX-XX-XXX_198X_XX-XX-XXX_XXXX_ALISON-DELLIT.json → data/person/ID_AU-01-CAN_198X_AU-01-CAN_XXXX_ALISON-DELLIT.json
View file

@ -1,11 +1,11 @@
{
"ppid": "ID_XX-XX-XXX_198X_XX-XX-XXX_XXXX_ALISON-DELLIT",
"ppid": "ID_AU-01-CAN_198X_AU-01-CAN_XXXX_ALISON-DELLIT",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-01-CAN",
"first_date": "198X",
"last_location": "XX-XX-XXX",
"last_location": "AU-01-CAN",
"last_date": "XXXX",
"name_tokens": [
"ALISON",
@ -14,7 +14,9 @@
"first_date_source": "inferred_birth_decade.primary_value",
"first_date_alternatives": [
"199X"
]
],
"first_location_source": "inferred_birth_settlement",
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "Alison Dellit",
@ -106,7 +108,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/alison-dellit-a575034_20251214T103840Z.json"
],
"modified_at": "2026-01-09T19:18:15.710720+00:00",
"modified_at": "2026-01-09T19:51:13.496689+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "alison-dellit-a575034",
@ -119,6 +121,17 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_198X_XX-XX-XXX_XXXX_ALISON-DELLIT",
"new_ppid": "ID_AU-01-CAN_198X_AU-01-CAN_XXXX_ALISON-DELLIT",
"changed_at": "2026-01-09T19:51:13.496687+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -133,7 +146,7 @@
"primary_rationale": "1988 is in 198X, but range extends into 199X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_experience_heuristic",
"inference_chain": [
{
"step": 1,
@ -182,7 +195,118 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 1988 spans decades 198X/199X",
"inferred_at": "2026-01-09T19:18:15.710701+00:00",
"inferred_at": "2026-01-09T19:51:13.482763+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_birth_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_job_location",
"inference_chain": [
{
"step": 1,
"observation": "Earliest job with location found (no education location available)",
"source_field": "profile_data.experience",
"source_value": {
"company": "National Library of Australia",
"title": "Business Architect, Libraries Australia, National Library Of Australia",
"date_range": "Sep 2011 - Oct 2012 • 1 year and 1 month",
"location": "Canberra, Australia"
}
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australia",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"First job location represents early life region"
],
"assumption_note": "Job location is weak proxy for birth location; person likely relocated for work",
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:51:13.487778+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_current_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "medium",
"inference_provenance": {
"method": "profile_location",
"inference_chain": [
{
"step": 1,
"observation": "Profile location field found",
"source_field": "profile_data.location",
"source_value": "Canberra, Australian Capital Territory, Australia (AU)"
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australian Capital Territory, Australia (AU)",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"Profile location is up-to-date",
"Profile location represents current residence"
],
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:51:13.496673+00:00",
"inferred_by": "enrich_ppids.py"
}
}

138
data/person/ID_XX-XX-XXX_198X_XX-XX-XXX_XXXX_ANTONIA-KASUNIC.json → data/person/ID_AU-01-CAN_198X_AU-01-CAN_XXXX_ANTONIA-KASUNIC.json
View file

@ -1,11 +1,11 @@
{
"ppid": "ID_XX-XX-XXX_198X_XX-XX-XXX_XXXX_ANTONIA-KASUNIC",
"ppid": "ID_AU-01-CAN_198X_AU-01-CAN_XXXX_ANTONIA-KASUNIC",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-01-CAN",
"first_date": "198X",
"last_location": "XX-XX-XXX",
"last_location": "AU-01-CAN",
"last_date": "XXXX",
"name_tokens": [
"ANTONIA",
@ -14,7 +14,9 @@
"first_date_source": "inferred_birth_decade.primary_value",
"first_date_alternatives": [
"199X"
]
],
"first_location_source": "inferred_birth_settlement",
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "Antonia Kasunic",
@ -99,7 +101,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/antonia-kasunic-80477051_20251214T103833Z.json"
],
"modified_at": "2026-01-09T19:18:16.605159+00:00",
"modified_at": "2026-01-09T19:51:20.530329+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "antonia-kasunic-80477051",
@ -112,6 +114,17 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_198X_XX-XX-XXX_XXXX_ANTONIA-KASUNIC",
"new_ppid": "ID_AU-01-CAN_198X_AU-01-CAN_XXXX_ANTONIA-KASUNIC",
"changed_at": "2026-01-09T19:51:20.530327+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -126,7 +139,7 @@
"primary_rationale": "1986 is in 198X, but range extends into 199X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_experience_heuristic",
"inference_chain": [
{
"step": 1,
@ -175,7 +188,118 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 1986 spans decades 198X/199X",
"inferred_at": "2026-01-09T19:18:16.605141+00:00",
"inferred_at": "2026-01-09T19:51:20.521156+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_birth_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_job_location",
"inference_chain": [
{
"step": 1,
"observation": "Earliest job with location found (no education location available)",
"source_field": "profile_data.experience",
"source_value": {
"company": "National Library of Australia",
"title": "Program Manager, Curatorial And Collection Research",
"date_range": "Sep 2020 - Present • 5 years and 2 months",
"location": "Canberra, Australian Capital Territory, Australia"
}
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australian Capital Territory, Australia",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"First job location represents early life region"
],
"assumption_note": "Job location is weak proxy for birth location; person likely relocated for work",
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:51:20.525817+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_current_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "medium",
"inference_provenance": {
"method": "profile_location",
"inference_chain": [
{
"step": 1,
"observation": "Profile location field found",
"source_field": "profile_data.location",
"source_value": "Canberra, Australian Capital Territory, Australia (AU)"
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australian Capital Territory, Australia (AU)",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"Profile location is up-to-date",
"Profile location represents current residence"
],
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:51:20.530321+00:00",
"inferred_by": "enrich_ppids.py"
}
}

27
data/person/ID_XX-XX-XXX_198X_XX-XX-XXX_XXXX_CATHY-PILGRIM.json → data/person/ID_AU-01-CAN_198X_AU-01-CAN_XXXX_CATHY-PILGRIM.json
View file

@ -1,11 +1,11 @@
{
"ppid": "ID_XX-XX-XXX_198X_XX-XX-XXX_XXXX_CATHY-PILGRIM",
"ppid": "ID_AU-01-CAN_198X_AU-01-CAN_XXXX_CATHY-PILGRIM",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-01-CAN",
"first_date": "198X",
"last_location": "XX-XX-XXX",
"last_location": "AU-01-CAN",
"last_date": "XXXX",
"name_tokens": [
"CATHY",
@ -14,7 +14,9 @@
"first_date_source": "inferred_birth_decade.primary_value",
"first_date_alternatives": [
"199X"
]
],
"first_location_source": "inferred_birth_settlement",
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "Cathy Pilgrim",
@ -102,7 +104,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/cathy-pilgrim-89b39124_20251214T103843Z.json"
],
"modified_at": "2026-01-09T19:18:12.367242+00:00",
"modified_at": "2026-01-09T19:51:29.287210+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "cathy-pilgrim-89b39124",
@ -115,6 +117,17 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_198X_XX-XX-XXX_XXXX_CATHY-PILGRIM",
"new_ppid": "ID_AU-01-CAN_198X_AU-01-CAN_XXXX_CATHY-PILGRIM",
"changed_at": "2026-01-09T19:47:59.589547+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -129,7 +142,7 @@
"primary_rationale": "1989 is in 198X, but range extends into 199X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_experience_heuristic",
"inference_chain": [
{
"step": 1,
@ -178,7 +191,7 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 1989 spans decades 198X/199X",
"inferred_at": "2026-01-09T19:18:12.367218+00:00",
"inferred_at": "2026-01-09T19:51:29.287206+00:00",
"inferred_by": "enrich_ppids.py"
}
}

138
data/person/ID_XX-XX-XXX_198X_XX-XX-XXX_XXXX_CLAYTON-ROGERS.json → data/person/ID_AU-01-CAN_198X_AU-01-CAN_XXXX_CLAYTON-ROGERS.json
View file

@ -1,11 +1,11 @@
{
"ppid": "ID_XX-XX-XXX_198X_XX-XX-XXX_XXXX_CLAYTON-ROGERS",
"ppid": "ID_AU-01-CAN_198X_AU-01-CAN_XXXX_CLAYTON-ROGERS",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-01-CAN",
"first_date": "198X",
"last_location": "XX-XX-XXX",
"last_location": "AU-01-CAN",
"last_date": "XXXX",
"name_tokens": [
"CLAYTON",
@ -14,7 +14,9 @@
"first_date_source": "inferred_birth_decade.primary_value",
"first_date_alternatives": [
"199X"
]
],
"first_location_source": "inferred_birth_settlement",
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "Clayton Rogers",
@ -98,7 +100,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/clayton-rogers-1b907987_20251214T103946Z.json"
],
"modified_at": "2026-01-09T19:18:13.427594+00:00",
"modified_at": "2026-01-09T19:50:54.156247+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "clayton-rogers-1b907987",
@ -111,6 +113,17 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_198X_XX-XX-XXX_XXXX_CLAYTON-ROGERS",
"new_ppid": "ID_AU-01-CAN_198X_AU-01-CAN_XXXX_CLAYTON-ROGERS",
"changed_at": "2026-01-09T19:50:54.156242+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -125,7 +138,7 @@
"primary_rationale": "1989 is in 198X, but range extends into 199X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_experience_heuristic",
"inference_chain": [
{
"step": 1,
@ -174,7 +187,118 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 1989 spans decades 198X/199X",
"inferred_at": "2026-01-09T19:18:13.427579+00:00",
"inferred_at": "2026-01-09T19:50:54.126023+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_birth_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_job_location",
"inference_chain": [
{
"step": 1,
"observation": "Earliest job with location found (no education location available)",
"source_field": "profile_data.experience",
"source_value": {
"company": "National Library of Australia",
"title": "A G Assistant Director, Cybersecurity",
"date_range": "Oct 2020 - Dec 2020 • 2 months",
"location": "Canberra, Australian Capital Territory, Australia"
}
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australian Capital Territory, Australia",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"First job location represents early life region"
],
"assumption_note": "Job location is weak proxy for birth location; person likely relocated for work",
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:50:54.141013+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_current_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "medium",
"inference_provenance": {
"method": "profile_location",
"inference_chain": [
{
"step": 1,
"observation": "Profile location field found",
"source_field": "profile_data.location",
"source_value": "Canberra, Australian Capital Territory, Australia (AU)"
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australian Capital Territory, Australia (AU)",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"Profile location is up-to-date",
"Profile location represents current residence"
],
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:50:54.156187+00:00",
"inferred_by": "enrich_ppids.py"
}
}

150
data/person/ID_XX-XX-XXX_198X_XX-XX-XXX_XXXX_FREYA-OCONNOR.json → data/person/ID_AU-01-CAN_198X_AU-01-CAN_XXXX_FREYA-OCONNOR.json
View file

@ -1,11 +1,11 @@
{
"ppid": "ID_XX-XX-XXX_198X_XX-XX-XXX_XXXX_FREYA-OCONNOR",
"ppid": "ID_AU-01-CAN_198X_AU-01-CAN_XXXX_FREYA-OCONNOR",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-01-CAN",
"first_date": "198X",
"last_location": "XX-XX-XXX",
"last_location": "AU-01-CAN",
"last_date": "XXXX",
"name_tokens": [
"FREYA",
@ -14,7 +14,9 @@
"first_date_source": "inferred_birth_decade.primary_value",
"first_date_alternatives": [
"199X"
]
],
"first_location_source": "inferred_birth_settlement",
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "Freya O'Connor",
@ -184,7 +186,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/freya-o-connor-6896a092_20251214T103829Z.json"
],
"modified_at": "2026-01-09T19:18:15.186614+00:00",
"modified_at": "2026-01-09T19:51:18.532345+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "freya-o-connor-6896a092",
@ -206,6 +208,17 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_198X_XX-XX-XXX_XXXX_FREYA-OCONNOR",
"new_ppid": "ID_AU-01-CAN_198X_AU-01-CAN_XXXX_FREYA-OCONNOR",
"changed_at": "2026-01-09T19:51:18.532342+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -220,7 +233,7 @@
"primary_rationale": "1987 is in 198X, but range extends into 199X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_education_heuristic",
"inference_chain": [
{
"step": 1,
@ -269,7 +282,130 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 1987 spans decades 198X/199X",
"inferred_at": "2026-01-09T19:18:15.186546+00:00",
"inferred_at": "2026-01-09T19:51:18.517725+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_birth_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "low",
"inference_provenance": {
"method": "earliest_education_location",
"inference_chain": [
{
"step": 1,
"observation": "Earliest education institution identified",
"source_field": "profile_data.education",
"source_value": {
"institution": "The Australian National University",
"date_range": "2009 - 2011 • 2 years",
"degree": "Bachelor's Degree, Bachelor of Arts, major in International Relations and Spanish"
}
},
{
"step": 2,
"lookup": "Institution location mapping",
"mapping_source": "DUTCH_UNI_LOCATIONS dictionary",
"mapping_key": "The Australian National University",
"mapping_result": "Canberra, Australia"
},
{
"step": 3,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australia",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 4,
"formatting": "CC-RR-PPP generation",
"components": {
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN"
},
"result": "AU-01-CAN"
}
],
"assumptions": [
"Student attended school near birth/family residence",
"Institution location is representative of early life location"
],
"assumption_note": "University location used as proxy for birth settlement; student may have relocated for education",
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:51:18.523626+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_current_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "medium",
"inference_provenance": {
"method": "profile_location",
"inference_chain": [
{
"step": 1,
"observation": "Profile location field found",
"source_field": "profile_data.location",
"source_value": "Canberra, Australian Capital Territory, Australia (AU)"
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australian Capital Territory, Australia (AU)",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"Profile location is up-to-date",
"Profile location represents current residence"
],
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:51:18.532321+00:00",
"inferred_by": "enrich_ppids.py"
}
}

138
data/person/ID_XX-XX-XXX_198X_XX-XX-XXX_XXXX_KARLEE-BAKER.json → data/person/ID_AU-01-CAN_198X_AU-01-CAN_XXXX_KARLEE-BAKER.json
View file

@ -1,11 +1,11 @@
{
"ppid": "ID_XX-XX-XXX_198X_XX-XX-XXX_XXXX_KARLEE-BAKER",
"ppid": "ID_AU-01-CAN_198X_AU-01-CAN_XXXX_KARLEE-BAKER",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-01-CAN",
"first_date": "198X",
"last_location": "XX-XX-XXX",
"last_location": "AU-01-CAN",
"last_date": "XXXX",
"name_tokens": [
"KARLEE",
@ -14,7 +14,9 @@
"first_date_source": "inferred_birth_decade",
"first_date_alternatives": [
"197X"
]
],
"first_location_source": "inferred_birth_settlement",
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "Karlee Baker",
@ -116,7 +118,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/karlee-baker-6a4651a8_20251214T104007Z.json"
],
"modified_at": "2026-01-09T19:18:13.459980+00:00",
"modified_at": "2026-01-09T19:50:54.463248+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "karlee-baker-6a4651a8",
@ -129,6 +131,17 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_198X_XX-XX-XXX_XXXX_KARLEE-BAKER",
"new_ppid": "ID_AU-01-CAN_198X_AU-01-CAN_XXXX_KARLEE-BAKER",
"changed_at": "2026-01-09T19:50:54.463246+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -137,7 +150,7 @@
"precision": "decade",
"confidence": "low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_education_heuristic",
"inference_chain": [
{
"step": 1,
@ -178,7 +191,118 @@
"Entry age for education/first job: 22 years (±3)",
"Career records are complete in LinkedIn profile"
],
"inferred_at": "2026-01-09T19:18:13.459943+00:00",
"inferred_at": "2026-01-09T19:50:54.446150+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_birth_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_job_location",
"inference_chain": [
{
"step": 1,
"observation": "Earliest job with location found (no education location available)",
"source_field": "profile_data.experience",
"source_value": {
"company": "National Museum of Australia",
"title": "Education Officer",
"date_range": "Jun 2020 - Apr 2021 • 10 months",
"location": "Canberra, Australian Capital Territory, Australia"
}
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australian Capital Territory, Australia",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"First job location represents early life region"
],
"assumption_note": "Job location is weak proxy for birth location; person likely relocated for work",
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:50:54.454743+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_current_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "medium",
"inference_provenance": {
"method": "profile_location",
"inference_chain": [
{
"step": 1,
"observation": "Profile location field found",
"source_field": "profile_data.location",
"source_value": "Canberra, Australian Capital Territory, Australia (AU)"
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australian Capital Territory, Australia (AU)",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"Profile location is up-to-date",
"Profile location represents current residence"
],
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:50:54.463234+00:00",
"inferred_by": "enrich_ppids.py"
}
}

138
data/person/ID_XX-XX-XXX_198X_XX-XX-XXX_XXXX_KELLY-SKYE.json → data/person/ID_AU-01-CAN_198X_AU-01-CAN_XXXX_KELLY-SKYE.json
View file

@ -1,11 +1,11 @@
{
"ppid": "ID_XX-XX-XXX_198X_XX-XX-XXX_XXXX_KELLY-SKYE",
"ppid": "ID_AU-01-CAN_198X_AU-01-CAN_XXXX_KELLY-SKYE",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-01-CAN",
"first_date": "198X",
"last_location": "XX-XX-XXX",
"last_location": "AU-01-CAN",
"last_date": "XXXX",
"name_tokens": [
"KELLY",
@ -14,7 +14,9 @@
"first_date_source": "inferred_birth_decade.primary_value",
"first_date_alternatives": [
"197X"
]
],
"first_location_source": "inferred_birth_settlement",
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "Kelly Skye",
@ -164,7 +166,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/kellyskye_20251214T103913Z.json"
],
"modified_at": "2026-01-09T19:18:18.204395+00:00",
"modified_at": "2026-01-09T19:51:29.211263+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "kellyskye",
@ -177,6 +179,17 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_198X_XX-XX-XXX_XXXX_KELLY-SKYE",
"new_ppid": "ID_AU-01-CAN_198X_AU-01-CAN_XXXX_KELLY-SKYE",
"changed_at": "2026-01-09T19:51:29.211260+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -191,7 +204,7 @@
"primary_rationale": "1984 is in 198X, but range extends into 197X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_experience_heuristic",
"inference_chain": [
{
"step": 1,
@ -240,7 +253,118 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 1984 spans decades 197X/198X",
"inferred_at": "2026-01-09T19:18:18.204358+00:00",
"inferred_at": "2026-01-09T19:51:29.174197+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_birth_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_job_location",
"inference_chain": [
{
"step": 1,
"observation": "Earliest job with location found (no education location available)",
"source_field": "profile_data.experience",
"source_value": {
"company": "Australian Government Department of Veterans' Affairs",
"title": "Senior Java Developer",
"date_range": "Aug 2017 - Aug 2018 • 1 year",
"location": "Canberra, Australia"
}
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australia",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"First job location represents early life region"
],
"assumption_note": "Job location is weak proxy for birth location; person likely relocated for work",
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:51:29.206351+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_current_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "medium",
"inference_provenance": {
"method": "profile_location",
"inference_chain": [
{
"step": 1,
"observation": "Profile location field found",
"source_field": "profile_data.location",
"source_value": "Canberra, Australian Capital Territory, Australia (AU)"
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australian Capital Territory, Australia (AU)",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"Profile location is up-to-date",
"Profile location represents current residence"
],
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:51:29.211249+00:00",
"inferred_by": "enrich_ppids.py"
}
}

149
data/person/ID_XX-XX-XXX_198X_XX-XX-XXX_XXXX_LUKE-HICKEY.json → data/person/ID_AU-01-CAN_198X_AU-01-CAN_XXXX_LUKE-HICKEY.json
View file

@ -1,11 +1,11 @@
{
"ppid": "ID_XX-XX-XXX_198X_XX-XX-XXX_XXXX_LUKE-HICKEY",
"ppid": "ID_AU-01-CAN_198X_AU-01-CAN_XXXX_LUKE-HICKEY",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-01-CAN",
"first_date": "198X",
"last_location": "XX-XX-XXX",
"last_location": "AU-01-CAN",
"last_date": "XXXX",
"name_tokens": [
"LUKE",
@ -14,7 +14,9 @@
"first_date_source": "inferred_birth_decade.primary_value",
"first_date_alternatives": [
"199X"
]
],
"first_location_source": "inferred_birth_settlement",
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "Luke Hickey",
@ -119,7 +121,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/luke-hickey-aab11b59_20251214T104010Z.json"
],
"modified_at": "2026-01-09T19:18:15.527958+00:00",
"modified_at": "2026-01-09T19:51:11.833477+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "luke-hickey-aab11b59",
@ -132,6 +134,17 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_198X_XX-XX-XXX_XXXX_LUKE-HICKEY",
"new_ppid": "ID_AU-01-CAN_198X_AU-01-CAN_XXXX_LUKE-HICKEY",
"changed_at": "2026-01-09T19:51:11.833474+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -146,7 +159,7 @@
"primary_rationale": "1987 is in 198X, but range extends into 199X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_experience_heuristic",
"inference_chain": [
{
"step": 1,
@ -195,7 +208,129 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 1987 spans decades 198X/199X",
"inferred_at": "2026-01-09T19:18:15.527935+00:00",
"inferred_at": "2026-01-09T19:51:11.807303+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_birth_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_job_location",
"inference_chain": [
{
"step": 1,
"observation": "Earliest job with location found (no education location available)",
"source_field": "profile_data.experience",
"source_value": {
"company": "Commonwealth Treasury",
"title": "GM Ministerial And Communications Division",
"date_range": "Jul 2012 - Mar 2016 • 3 years and 8 months",
"location": "General Manager, Ministerial and Communications division"
}
},
{
"step": 2,
"observation": "Earliest job with location found (no education location available)",
"source_field": "profile_data.experience",
"source_value": {
"company": "Department of Parliamentary Services",
"title": "Assistant Secretary, Parliamentary Experience Branch",
"date_range": "Mar 2016 - Dec 2019 • 3 years and 9 months",
"location": "Canberra, Australia"
}
},
{
"step": 3,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australia",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 4,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"First job location represents early life region"
],
"assumption_note": "Job location is weak proxy for birth location; person likely relocated for work",
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:51:11.821775+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_current_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "medium",
"inference_provenance": {
"method": "profile_location",
"inference_chain": [
{
"step": 1,
"observation": "Profile location field found",
"source_field": "profile_data.location",
"source_value": "Canberra, Australian Capital Territory, Australia (AU)"
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australian Capital Territory, Australia (AU)",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"Profile location is up-to-date",
"Profile location represents current residence"
],
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:51:11.833443+00:00",
"inferred_by": "enrich_ppids.py"
}
}

138
data/person/ID_XX-XX-XXX_198X_XX-XX-XXX_XXXX_REBECCA-PENDLEBURY.json → data/person/ID_AU-01-CAN_198X_AU-01-CAN_XXXX_REBECCA-PENDLEBURY.json
View file

@ -1,11 +1,11 @@
{
"ppid": "ID_XX-XX-XXX_198X_XX-XX-XXX_XXXX_REBECCA-PENDLEBURY",
"ppid": "ID_AU-01-CAN_198X_AU-01-CAN_XXXX_REBECCA-PENDLEBURY",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-01-CAN",
"first_date": "198X",
"last_location": "XX-XX-XXX",
"last_location": "AU-01-CAN",
"last_date": "XXXX",
"name_tokens": [
"REBECCA",
@ -14,7 +14,9 @@
"first_date_source": "inferred_birth_decade.primary_value",
"first_date_alternatives": [
"199X"
]
],
"first_location_source": "inferred_birth_settlement",
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "Rebecca Pendlebury",
@ -99,7 +101,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/rebecca-pendlebury-78790b133_20251214T103801Z.json"
],
"modified_at": "2026-01-09T19:18:17.395733+00:00",
"modified_at": "2026-01-09T19:51:26.704559+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "rebecca-pendlebury-78790b133",
@ -112,6 +114,17 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_198X_XX-XX-XXX_XXXX_REBECCA-PENDLEBURY",
"new_ppid": "ID_AU-01-CAN_198X_AU-01-CAN_XXXX_REBECCA-PENDLEBURY",
"changed_at": "2026-01-09T19:51:26.704557+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -126,7 +139,7 @@
"primary_rationale": "1987 is in 198X, but range extends into 199X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_experience_heuristic",
"inference_chain": [
{
"step": 1,
@ -175,7 +188,118 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 1987 spans decades 198X/199X",
"inferred_at": "2026-01-09T19:18:17.395711+00:00",
"inferred_at": "2026-01-09T19:51:26.691694+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_birth_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_job_location",
"inference_chain": [
{
"step": 1,
"observation": "Earliest job with location found (no education location available)",
"source_field": "profile_data.experience",
"source_value": {
"company": "National Library of Australia",
"title": "Test Analyst",
"date_range": "Jun 2019 - Mar 2020 • 9 months",
"location": "Canberra, Australia"
}
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australia",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"First job location represents early life region"
],
"assumption_note": "Job location is weak proxy for birth location; person likely relocated for work",
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:51:26.698701+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_current_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "medium",
"inference_provenance": {
"method": "profile_location",
"inference_chain": [
{
"step": 1,
"observation": "Profile location field found",
"source_field": "profile_data.location",
"source_value": "Canberra, Australian Capital Territory, Australia (AU)"
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australian Capital Territory, Australia (AU)",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"Profile location is up-to-date",
"Profile location represents current residence"
],
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:51:26.704545+00:00",
"inferred_by": "enrich_ppids.py"
}
}

27
data/person/ID_XX-XX-XXX_198X_XX-XX-XXX_XXXX_RENATA-DYER.json → data/person/ID_AU-01-CAN_198X_AU-01-CAN_XXXX_RENATA-DYER.json
View file

@ -1,11 +1,11 @@
{
"ppid": "ID_XX-XX-XXX_198X_XX-XX-XXX_XXXX_RENATA-DYER",
"ppid": "ID_AU-01-CAN_198X_AU-01-CAN_XXXX_RENATA-DYER",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-01-CAN",
"first_date": "198X",
"last_location": "XX-XX-XXX",
"last_location": "AU-01-CAN",
"last_date": "XXXX",
"name_tokens": [
"RENATA",
@ -14,7 +14,9 @@
"first_date_source": "inferred_birth_decade.primary_value",
"first_date_alternatives": [
"197X"
]
],
"first_location_source": "inferred_birth_settlement",
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "Renata Dyer",
@ -187,7 +189,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/renatadyer_20251214T103748Z.json"
],
"modified_at": "2026-01-09T19:18:11.678087+00:00",
"modified_at": "2026-01-09T19:51:28.154649+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "renatadyer",
@ -200,6 +202,17 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_198X_XX-XX-XXX_XXXX_RENATA-DYER",
"new_ppid": "ID_AU-01-CAN_198X_AU-01-CAN_XXXX_RENATA-DYER",
"changed_at": "2026-01-09T19:47:58.767529+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -214,7 +227,7 @@
"primary_rationale": "1981 is in 198X, but range extends into 197X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_education_heuristic",
"inference_chain": [
{
"step": 1,
@ -263,7 +276,7 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 1981 spans decades 197X/198X",
"inferred_at": "2026-01-09T19:18:11.677945+00:00",
"inferred_at": "2026-01-09T19:51:28.154641+00:00",
"inferred_by": "enrich_ppids.py"
}
}

150
data/person/ID_XX-XX-XXX_198X_XX-XX-XXX_XXXX_RHYS-C.json → data/person/ID_AU-01-CAN_198X_AU-01-CAN_XXXX_RHYS-C.json
View file

@ -1,17 +1,19 @@
{
"ppid": "ID_XX-XX-XXX_198X_XX-XX-XXX_XXXX_RHYS-C",
"ppid": "ID_AU-01-CAN_198X_AU-01-CAN_XXXX_RHYS-C",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-01-CAN",
"first_date": "198X",
"last_location": "XX-XX-XXX",
"last_location": "AU-01-CAN",
"last_date": "XXXX",
"name_tokens": [
"RHYS",
"C"
],
"first_date_source": "inferred_birth_decade"
"first_date_source": "inferred_birth_decade",
"first_location_source": "inferred_birth_settlement",
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "Rhys C.",
@ -91,7 +93,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/rhys-c-444929136_20251214T103800Z.json"
],
"modified_at": "2026-01-09T19:18:14.745347+00:00",
"modified_at": "2026-01-09T19:51:04.008120+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "rhys-c-444929136",
@ -104,6 +106,17 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_198X_XX-XX-XXX_XXXX_RHYS-C",
"new_ppid": "ID_AU-01-CAN_198X_AU-01-CAN_XXXX_RHYS-C",
"changed_at": "2026-01-09T19:51:04.008118+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -112,7 +125,7 @@
"precision": "decade",
"confidence": "low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_education_heuristic",
"inference_chain": [
{
"step": 1,
@ -153,7 +166,130 @@
"Entry age for education/first job: 18 years (±3)",
"Career records are complete in LinkedIn profile"
],
"inferred_at": "2026-01-09T19:18:14.745313+00:00",
"inferred_at": "2026-01-09T19:51:03.995827+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_birth_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "low",
"inference_provenance": {
"method": "earliest_education_location",
"inference_chain": [
{
"step": 1,
"observation": "Earliest education institution identified",
"source_field": "profile_data.education",
"source_value": {
"institution": "The Australian National University",
"date_range": "2003 - 2010 • 7 years",
"degree": "Bachelor of Asian Studies (Specialist), Chinese Studies"
}
},
{
"step": 2,
"lookup": "Institution location mapping",
"mapping_source": "DUTCH_UNI_LOCATIONS dictionary",
"mapping_key": "The Australian National University",
"mapping_result": "Canberra, Australia"
},
{
"step": 3,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australia",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 4,
"formatting": "CC-RR-PPP generation",
"components": {
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN"
},
"result": "AU-01-CAN"
}
],
"assumptions": [
"Student attended school near birth/family residence",
"Institution location is representative of early life location"
],
"assumption_note": "University location used as proxy for birth settlement; student may have relocated for education",
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:51:04.002447+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_current_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "medium",
"inference_provenance": {
"method": "profile_location",
"inference_chain": [
{
"step": 1,
"observation": "Profile location field found",
"source_field": "profile_data.location",
"source_value": "Canberra, Australian Capital Territory, Australia (AU)"
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australian Capital Territory, Australia (AU)",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"Profile location is up-to-date",
"Profile location represents current residence"
],
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:51:04.008109+00:00",
"inferred_by": "enrich_ppids.py"
}
}

138
data/person/ID_XX-XX-XXX_198X_XX-XX-XXX_XXXX_ROBYN-HOLMES.json → data/person/ID_AU-01-CAN_198X_AU-01-CAN_XXXX_ROBYN-HOLMES.json
View file

@ -1,11 +1,11 @@
{
"ppid": "ID_XX-XX-XXX_198X_XX-XX-XXX_XXXX_ROBYN-HOLMES",
"ppid": "ID_AU-01-CAN_198X_AU-01-CAN_XXXX_ROBYN-HOLMES",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-01-CAN",
"first_date": "198X",
"last_location": "XX-XX-XXX",
"last_location": "AU-01-CAN",
"last_date": "XXXX",
"name_tokens": [
"ROBYN",
@ -14,7 +14,9 @@
"first_date_source": "inferred_birth_decade.primary_value",
"first_date_alternatives": [
"199X"
]
],
"first_location_source": "inferred_birth_settlement",
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "Robyn Holmes",
@ -104,7 +106,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/robyn-holmes-a126805_20251214T103927Z.json"
],
"modified_at": "2026-01-09T19:18:14.197990+00:00",
"modified_at": "2026-01-09T19:50:58.857331+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "robyn-holmes-a126805",
@ -117,6 +119,17 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_198X_XX-XX-XXX_XXXX_ROBYN-HOLMES",
"new_ppid": "ID_AU-01-CAN_198X_AU-01-CAN_XXXX_ROBYN-HOLMES",
"changed_at": "2026-01-09T19:50:58.857328+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -131,7 +144,7 @@
"primary_rationale": "1988 is in 198X, but range extends into 199X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_experience_heuristic",
"inference_chain": [
{
"step": 1,
@ -180,7 +193,118 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 1988 spans decades 198X/199X",
"inferred_at": "2026-01-09T19:18:14.197974+00:00",
"inferred_at": "2026-01-09T19:50:58.826627+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_birth_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_job_location",
"inference_chain": [
{
"step": 1,
"observation": "Earliest job with location found (no education location available)",
"source_field": "profile_data.experience",
"source_value": {
"company": "National Library of Australia",
"title": "Senior Curator And Fellowships Secretary, Formerly Curator Of Music",
"date_range": "Jan 2011 - Present • 7 years and 9 months",
"location": "Canberra, ACT, Australia"
}
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Canberra, ACT, Australia",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"First job location represents early life region"
],
"assumption_note": "Job location is weak proxy for birth location; person likely relocated for work",
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:50:58.839694+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_current_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "medium",
"inference_provenance": {
"method": "profile_location",
"inference_chain": [
{
"step": 1,
"observation": "Profile location field found",
"source_field": "profile_data.location",
"source_value": "Canberra, Australian Capital Territory, Australia (AU)"
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australian Capital Territory, Australia (AU)",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"Profile location is up-to-date",
"Profile location represents current residence"
],
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:50:58.857307+00:00",
"inferred_by": "enrich_ppids.py"
}
}

138
data/person/ID_XX-XX-XXX_198X_XX-XX-XXX_XXXX_ROD-STROUD.json → data/person/ID_AU-01-CAN_198X_AU-01-CAN_XXXX_ROD-STROUD.json
View file

@ -1,11 +1,11 @@
{
"ppid": "ID_XX-XX-XXX_198X_XX-XX-XXX_XXXX_ROD-STROUD",
"ppid": "ID_AU-01-CAN_198X_AU-01-CAN_XXXX_ROD-STROUD",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-01-CAN",
"first_date": "198X",
"last_location": "XX-XX-XXX",
"last_location": "AU-01-CAN",
"last_date": "XXXX",
"name_tokens": [
"ROD",
@ -14,7 +14,9 @@
"first_date_source": "inferred_birth_decade.primary_value",
"first_date_alternatives": [
"197X"
]
],
"first_location_source": "inferred_birth_settlement",
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "Rod Stroud",
@ -91,7 +93,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/rod-stroud-40888533_20251214T103840Z.json"
],
"modified_at": "2026-01-09T19:18:15.688528+00:00",
"modified_at": "2026-01-09T19:51:13.459931+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "rod-stroud-40888533",
@ -104,6 +106,17 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_198X_XX-XX-XXX_XXXX_ROD-STROUD",
"new_ppid": "ID_AU-01-CAN_198X_AU-01-CAN_XXXX_ROD-STROUD",
"changed_at": "2026-01-09T19:51:13.459912+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -118,7 +131,7 @@
"primary_rationale": "1981 is in 198X, but range extends into 197X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_experience_heuristic",
"inference_chain": [
{
"step": 1,
@ -167,7 +180,118 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 1981 spans decades 197X/198X",
"inferred_at": "2026-01-09T19:18:15.688513+00:00",
"inferred_at": "2026-01-09T19:51:13.443042+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_birth_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_job_location",
"inference_chain": [
{
"step": 1,
"observation": "Earliest job with location found (no education location available)",
"source_field": "profile_data.experience",
"source_value": {
"company": "Australian Institute of Aboriginal and Torres Strait Islander Studies",
"title": "Library Director",
"date_range": "Sep 2004 - Aug 2012 • 7 years and 11 months",
"location": "Canberra, Australia"
}
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australia",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"First job location represents early life region"
],
"assumption_note": "Job location is weak proxy for birth location; person likely relocated for work",
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:51:13.448984+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_current_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "medium",
"inference_provenance": {
"method": "profile_location",
"inference_chain": [
{
"step": 1,
"observation": "Profile location field found",
"source_field": "profile_data.location",
"source_value": "Canberra, Australian Capital Territory, Australia (AU)"
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australian Capital Territory, Australia (AU)",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"Profile location is up-to-date",
"Profile location represents current residence"
],
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:51:13.459872+00:00",
"inferred_by": "enrich_ppids.py"
}
}

160
data/person/ID_XX-XX-XXX_198X_XX-XX-XXX_XXXX_VEERIN-C.json → data/person/ID_AU-01-CAN_198X_AU-06-FRA_XXXX_VEERIN-C.json
View file

@ -1,11 +1,11 @@
{
"ppid": "ID_XX-XX-XXX_198X_XX-XX-XXX_XXXX_VEERIN-C",
"ppid": "ID_AU-01-CAN_198X_AU-06-FRA_XXXX_VEERIN-C",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-01-CAN",
"first_date": "198X",
"last_location": "XX-XX-XXX",
"last_location": "AU-06-FRA",
"last_date": "XXXX",
"name_tokens": [
"VEERIN",
@ -14,7 +14,9 @@
"first_date_source": "inferred_birth_decade.primary_value",
"first_date_alternatives": [
"199X"
]
],
"first_location_source": "inferred_birth_settlement",
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "Veerin C.",
@ -233,7 +235,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/veerin-c-312b0716_20251214T103932Z.json"
],
"modified_at": "2026-01-09T19:18:17.214248+00:00",
"modified_at": "2026-01-09T19:51:25.460451+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "veerin-c-312b0716",
@ -246,6 +248,17 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_198X_XX-XX-XXX_XXXX_VEERIN-C",
"new_ppid": "ID_AU-01-CAN_198X_AU-06-FRA_XXXX_VEERIN-C",
"changed_at": "2026-01-09T19:51:25.460449+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -260,7 +273,7 @@
"primary_rationale": "1987 is in 198X, but range extends into 199X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_experience_heuristic",
"inference_chain": [
{
"step": 1,
@ -309,7 +322,140 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 1987 spans decades 198X/199X",
"inferred_at": "2026-01-09T19:18:17.214208+00:00",
"inferred_at": "2026-01-09T19:51:25.391154+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_birth_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_job_location",
"inference_chain": [
{
"step": 1,
"observation": "Earliest job with location found (no education location available)",
"source_field": "profile_data.experience",
"source_value": {
"company": "Fortuneplace Apartments Chiangrai, Thailand",
"title": "Co-Owner",
"date_range": "Jun 2010 - Jun 2023 • 13 years",
"location": "Chiangrai"
}
},
{
"step": 2,
"observation": "Earliest job with location found (no education location available)",
"source_field": "profile_data.experience",
"source_value": {
"company": "JJ Autocar Used Car Dealership, Thailand",
"title": "Business Owner",
"date_range": "Mar 2010 - Nov 2011 • 1 year and 8 months",
"location": "Chiang Rai, Thailand"
}
},
{
"step": 3,
"observation": "Earliest job with location found (no education location available)",
"source_field": "profile_data.experience",
"source_value": {
"company": "Mocca Espresso Lounge",
"title": "Floor Staff",
"date_range": "Mar 2012 - Jun 2013 • 1 year and 3 months",
"location": "Canberra, Australia"
}
},
{
"step": 4,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australia",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 5,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"First job location represents early life region"
],
"assumption_note": "Job location is weak proxy for birth location; person likely relocated for work",
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:51:25.455479+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_current_settlement": {
"value": "Franklin",
"formatted": "AU-06-FRA",
"country_code": "AU",
"region_code": "06",
"settlement_code": "FRA",
"confidence": "medium",
"inference_provenance": {
"method": "profile_location",
"inference_chain": [
{
"step": 1,
"observation": "Profile location field found",
"source_field": "profile_data.location",
"source_value": "Franklin, Australian Capital Territory, Australia (AU)"
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Franklin, Australian Capital Territory, Australia (AU)",
"result": {
"geonames_id": 2166160,
"geonames_name": "Franklin",
"admin1_code": "06",
"admin1_name": "Tasmania",
"feature_code": "PPL",
"latitude": -43.08884,
"longitude": 147.00906
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-06-FRA"
}
],
"assumptions": [
"Profile location is up-to-date",
"Profile location represents current residence"
],
"geonames_data": {
"geonames_id": 2166160,
"geonames_name": "Franklin",
"admin1_code": "06",
"admin1_name": "Tasmania",
"feature_code": "PPL",
"latitude": -43.08884,
"longitude": 147.00906
},
"inferred_at": "2026-01-09T19:51:25.460438+00:00",
"inferred_by": "enrich_ppids.py"
}
}

138
data/person/ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_ADRIA-HU.json → data/person/ID_AU-01-CAN_199X_AU-01-CAN_XXXX_ADRIA-HU.json
View file

@ -1,11 +1,11 @@
{
"ppid": "ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_ADRIA-HU",
"ppid": "ID_AU-01-CAN_199X_AU-01-CAN_XXXX_ADRIA-HU",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-01-CAN",
"first_date": "199X",
"last_location": "XX-XX-XXX",
"last_location": "AU-01-CAN",
"last_date": "XXXX",
"name_tokens": [
"ADRIA",
@ -14,7 +14,9 @@
"first_date_source": "inferred_birth_decade.primary_value",
"first_date_alternatives": [
"198X"
]
],
"first_location_source": "inferred_birth_settlement",
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "Adria Hu",
@ -91,7 +93,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/adria-hu-a901701a_20251214T103931Z.json"
],
"modified_at": "2026-01-09T19:18:16.269988+00:00",
"modified_at": "2026-01-09T19:51:18.361059+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "adria-hu-a901701a",
@ -104,6 +106,17 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_ADRIA-HU",
"new_ppid": "ID_AU-01-CAN_199X_AU-01-CAN_XXXX_ADRIA-HU",
"changed_at": "2026-01-09T19:51:18.361056+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -118,7 +131,7 @@
"primary_rationale": "1994 is in 199X, but range extends into 198X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_experience_heuristic",
"inference_chain": [
{
"step": 1,
@ -167,7 +180,118 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 1994 spans decades 198X/199X",
"inferred_at": "2026-01-09T19:18:16.269933+00:00",
"inferred_at": "2026-01-09T19:51:18.350149+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_birth_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_job_location",
"inference_chain": [
{
"step": 1,
"observation": "Earliest job with location found (no education location available)",
"source_field": "profile_data.experience",
"source_value": {
"company": "National Museum of Australia",
"title": "Project Officer",
"date_range": "Jul 2017 - Present • 8 years and 4 months",
"location": "Canberra, Australia"
}
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australia",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"First job location represents early life region"
],
"assumption_note": "Job location is weak proxy for birth location; person likely relocated for work",
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:51:18.356324+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_current_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "medium",
"inference_provenance": {
"method": "profile_location",
"inference_chain": [
{
"step": 1,
"observation": "Profile location field found",
"source_field": "profile_data.location",
"source_value": "Canberra, Australian Capital Territory, Australia (AU)"
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australian Capital Territory, Australia (AU)",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"Profile location is up-to-date",
"Profile location represents current residence"
],
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:51:18.361050+00:00",
"inferred_by": "enrich_ppids.py"
}
}

149
data/person/ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_ADRIANNA-FULLERTON.json → data/person/ID_AU-01-CAN_199X_AU-01-CAN_XXXX_ADRIANNA-FULLERTON.json
View file

@ -1,11 +1,11 @@
{
"ppid": "ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_ADRIANNA-FULLERTON",
"ppid": "ID_AU-01-CAN_199X_AU-01-CAN_XXXX_ADRIANNA-FULLERTON",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-01-CAN",
"first_date": "199X",
"last_location": "XX-XX-XXX",
"last_location": "AU-01-CAN",
"last_date": "XXXX",
"name_tokens": [
"ADRIANNA",
@ -14,7 +14,9 @@
"first_date_source": "inferred_birth_decade.primary_value",
"first_date_alternatives": [
"200X"
]
],
"first_location_source": "inferred_birth_settlement",
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "Adrianna Fullerton",
@ -130,7 +132,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/adrianna-fullerton-68074193_20251214T103959Z.json"
],
"modified_at": "2026-01-09T19:18:16.437042+00:00",
"modified_at": "2026-01-09T19:51:18.501651+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "adrianna-fullerton-68074193",
@ -143,6 +145,17 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_ADRIANNA-FULLERTON",
"new_ppid": "ID_AU-01-CAN_199X_AU-01-CAN_XXXX_ADRIANNA-FULLERTON",
"changed_at": "2026-01-09T19:51:18.501648+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -157,7 +170,7 @@
"primary_rationale": "1995 is in 199X, but range extends into 200X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_experience_heuristic",
"inference_chain": [
{
"step": 1,
@ -206,7 +219,129 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 1995 spans decades 199X/200X",
"inferred_at": "2026-01-09T19:18:16.437020+00:00",
"inferred_at": "2026-01-09T19:51:18.490345+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_birth_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_job_location",
"inference_chain": [
{
"step": 1,
"observation": "Earliest job with location found (no education location available)",
"source_field": "profile_data.experience",
"source_value": {
"company": "National Library of Australia",
"title": "Manuscripts Acquisitions Team Leader",
"date_range": "Mar 2018 - Jan 2021 • 2 years and 10 months",
"location": "Canberra"
}
},
{
"step": 2,
"observation": "Earliest job with location found (no education location available)",
"source_field": "profile_data.experience",
"source_value": {
"company": "National Library of Australia",
"title": "Coordinator, Acquisitions",
"date_range": "Jan 2021 - Jun 2022 • 1 year and 5 months",
"location": "Canberra, Australian Capital Territory, Australia"
}
},
{
"step": 3,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australian Capital Territory, Australia",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 4,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"First job location represents early life region"
],
"assumption_note": "Job location is weak proxy for birth location; person likely relocated for work",
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:51:18.495269+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_current_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "medium",
"inference_provenance": {
"method": "profile_location",
"inference_chain": [
{
"step": 1,
"observation": "Profile location field found",
"source_field": "profile_data.location",
"source_value": "Canberra, Australian Capital Territory, Australia (AU)"
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australian Capital Territory, Australia (AU)",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"Profile location is up-to-date",
"Profile location represents current residence"
],
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:51:18.501629+00:00",
"inferred_by": "enrich_ppids.py"
}
}

150
data/person/ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_ALLISTER-MILLS.json → data/person/ID_AU-01-CAN_199X_AU-01-CAN_XXXX_ALLISTER-MILLS.json
View file

@ -1,11 +1,11 @@
{
"ppid": "ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_ALLISTER-MILLS",
"ppid": "ID_AU-01-CAN_199X_AU-01-CAN_XXXX_ALLISTER-MILLS",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-01-CAN",
"first_date": "199X",
"last_location": "XX-XX-XXX",
"last_location": "AU-01-CAN",
"last_date": "XXXX",
"name_tokens": [
"ALLISTER",
@ -14,7 +14,9 @@
"first_date_source": "inferred_birth_decade",
"first_date_alternatives": [
"200X"
]
],
"first_location_source": "inferred_birth_settlement",
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "Allister Mills",
@ -122,7 +124,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/allister-mills-180619137_20251214T104004Z.json"
],
"modified_at": "2026-01-09T19:18:14.869757+00:00",
"modified_at": "2026-01-09T19:51:05.252362+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "allister-mills-180619137",
@ -135,6 +137,17 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_ALLISTER-MILLS",
"new_ppid": "ID_AU-01-CAN_199X_AU-01-CAN_XXXX_ALLISTER-MILLS",
"changed_at": "2026-01-09T19:51:05.252340+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -143,7 +156,7 @@
"precision": "decade",
"confidence": "low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_education_heuristic",
"inference_chain": [
{
"step": 1,
@ -184,7 +197,130 @@
"Entry age for education/first job: 22 years (±3)",
"Career records are complete in LinkedIn profile"
],
"inferred_at": "2026-01-09T19:18:14.869717+00:00",
"inferred_at": "2026-01-09T19:51:05.215714+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_birth_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "low",
"inference_provenance": {
"method": "earliest_education_location",
"inference_chain": [
{
"step": 1,
"observation": "Earliest education institution identified",
"source_field": "profile_data.education",
"source_value": {
"institution": "The Australian National University",
"date_range": "2016 - 2017 • 1 year",
"degree": "Master of museum and heritage studies, Museums and Collections, Commendation"
}
},
{
"step": 2,
"lookup": "Institution location mapping",
"mapping_source": "DUTCH_UNI_LOCATIONS dictionary",
"mapping_key": "The Australian National University",
"mapping_result": "Canberra, Australia"
},
{
"step": 3,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australia",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 4,
"formatting": "CC-RR-PPP generation",
"components": {
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN"
},
"result": "AU-01-CAN"
}
],
"assumptions": [
"Student attended school near birth/family residence",
"Institution location is representative of early life location"
],
"assumption_note": "University location used as proxy for birth settlement; student may have relocated for education",
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:51:05.235279+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_current_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "medium",
"inference_provenance": {
"method": "profile_location",
"inference_chain": [
{
"step": 1,
"observation": "Profile location field found",
"source_field": "profile_data.location",
"source_value": "Canberra, Australian Capital Territory, Australia (AU)"
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australian Capital Territory, Australia (AU)",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"Profile location is up-to-date",
"Profile location represents current residence"
],
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:51:05.252194+00:00",
"inferred_by": "enrich_ppids.py"
}
}

150
data/person/ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_ANNE-ROWLANDS.json → data/person/ID_AU-01-CAN_199X_AU-01-CAN_XXXX_ANNE-ROWLANDS.json
View file

@ -1,11 +1,11 @@
{
"ppid": "ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_ANNE-ROWLANDS",
"ppid": "ID_AU-01-CAN_199X_AU-01-CAN_XXXX_ANNE-ROWLANDS",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-01-CAN",
"first_date": "199X",
"last_location": "XX-XX-XXX",
"last_location": "AU-01-CAN",
"last_date": "XXXX",
"name_tokens": [
"ANNE",
@ -14,7 +14,9 @@
"first_date_source": "inferred_birth_decade.primary_value",
"first_date_alternatives": [
"198X"
]
],
"first_location_source": "inferred_birth_settlement",
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "Anne Rowlands",
@ -231,7 +233,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/anne-rowlands-3873a451_20251214T103939Z.json"
],
"modified_at": "2026-01-09T19:18:15.577166+00:00",
"modified_at": "2026-01-09T19:51:12.177947+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "anne-rowlands-3873a451",
@ -244,6 +246,17 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_ANNE-ROWLANDS",
"new_ppid": "ID_AU-01-CAN_199X_AU-01-CAN_XXXX_ANNE-ROWLANDS",
"changed_at": "2026-01-09T19:51:12.177945+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -258,7 +271,7 @@
"primary_rationale": "1990 is in 199X, but range extends into 198X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_education_heuristic",
"inference_chain": [
{
"step": 1,
@ -307,7 +320,130 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 1990 spans decades 198X/199X",
"inferred_at": "2026-01-09T19:18:15.577093+00:00",
"inferred_at": "2026-01-09T19:51:12.123846+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_birth_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "low",
"inference_provenance": {
"method": "earliest_education_location",
"inference_chain": [
{
"step": 1,
"observation": "Earliest education institution identified",
"source_field": "profile_data.education",
"source_value": {
"institution": "University of Canberra",
"date_range": "2012 - 2013 • 1 year",
"degree": "Master of Library & Information Science (MLIS), Library and Information Science"
}
},
{
"step": 2,
"lookup": "Institution location mapping",
"mapping_source": "DUTCH_UNI_LOCATIONS dictionary",
"mapping_key": "University of Canberra",
"mapping_result": "Canberra, Australia"
},
{
"step": 3,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australia",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 4,
"formatting": "CC-RR-PPP generation",
"components": {
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN"
},
"result": "AU-01-CAN"
}
],
"assumptions": [
"Student attended school near birth/family residence",
"Institution location is representative of early life location"
],
"assumption_note": "University location used as proxy for birth settlement; student may have relocated for education",
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:51:12.170135+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_current_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "medium",
"inference_provenance": {
"method": "profile_location",
"inference_chain": [
{
"step": 1,
"observation": "Profile location field found",
"source_field": "profile_data.location",
"source_value": "Canberra, Australian Capital Territory, Australia (AU)"
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australian Capital Territory, Australia (AU)",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"Profile location is up-to-date",
"Profile location represents current residence"
],
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:51:12.177926+00:00",
"inferred_by": "enrich_ppids.py"
}
}

150
data/person/ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_BELLE-WILSON.json → data/person/ID_AU-01-CAN_199X_AU-01-CAN_XXXX_BELLE-WILSON.json
View file

@ -1,11 +1,11 @@
{
"ppid": "ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_BELLE-WILSON",
"ppid": "ID_AU-01-CAN_199X_AU-01-CAN_XXXX_BELLE-WILSON",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-01-CAN",
"first_date": "199X",
"last_location": "XX-XX-XXX",
"last_location": "AU-01-CAN",
"last_date": "XXXX",
"name_tokens": [
"BELLE",
@ -14,7 +14,9 @@
"first_date_source": "inferred_birth_decade.primary_value",
"first_date_alternatives": [
"200X"
]
],
"first_location_source": "inferred_birth_settlement",
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "Belle Wilson",
@ -119,7 +121,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/belle-wilson-7163ab195_20251214T103805Z.json"
],
"modified_at": "2026-01-09T19:18:13.600263+00:00",
"modified_at": "2026-01-09T19:50:57.778400+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "belle-wilson-7163ab195",
@ -141,6 +143,17 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_BELLE-WILSON",
"new_ppid": "ID_AU-01-CAN_199X_AU-01-CAN_XXXX_BELLE-WILSON",
"changed_at": "2026-01-09T19:50:57.778396+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -155,7 +168,7 @@
"primary_rationale": "1998 is in 199X, but range extends into 200X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_education_heuristic",
"inference_chain": [
{
"step": 1,
@ -204,7 +217,130 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 1998 spans decades 199X/200X",
"inferred_at": "2026-01-09T19:18:13.600218+00:00",
"inferred_at": "2026-01-09T19:50:57.750060+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_birth_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "low",
"inference_provenance": {
"method": "earliest_education_location",
"inference_chain": [
{
"step": 1,
"observation": "Earliest education institution identified",
"source_field": "profile_data.education",
"source_value": {
"institution": "The Australian National University",
"date_range": "2020 - 2021 • 1 year",
"degree": "Master of Art History and Curatorial Studies, 6.75"
}
},
{
"step": 2,
"lookup": "Institution location mapping",
"mapping_source": "DUTCH_UNI_LOCATIONS dictionary",
"mapping_key": "The Australian National University",
"mapping_result": "Canberra, Australia"
},
{
"step": 3,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australia",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 4,
"formatting": "CC-RR-PPP generation",
"components": {
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN"
},
"result": "AU-01-CAN"
}
],
"assumptions": [
"Student attended school near birth/family residence",
"Institution location is representative of early life location"
],
"assumption_note": "University location used as proxy for birth settlement; student may have relocated for education",
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:50:57.759754+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_current_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "medium",
"inference_provenance": {
"method": "profile_location",
"inference_chain": [
{
"step": 1,
"observation": "Profile location field found",
"source_field": "profile_data.location",
"source_value": "Canberra, Australian Capital Territory, Australia (AU)"
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australian Capital Territory, Australia (AU)",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"Profile location is up-to-date",
"Profile location represents current residence"
],
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:50:57.778372+00:00",
"inferred_by": "enrich_ppids.py"
}
}

150
data/person/ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_BEN-PRATTEN.json → data/person/ID_AU-01-CAN_199X_AU-01-CAN_XXXX_BEN-PRATTEN.json
View file

@ -1,11 +1,11 @@
{
"ppid": "ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_BEN-PRATTEN",
"ppid": "ID_AU-01-CAN_199X_AU-01-CAN_XXXX_BEN-PRATTEN",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-01-CAN",
"first_date": "199X",
"last_location": "XX-XX-XXX",
"last_location": "AU-01-CAN",
"last_date": "XXXX",
"name_tokens": [
"BEN",
@ -14,7 +14,9 @@
"first_date_source": "inferred_birth_decade.primary_value",
"first_date_alternatives": [
"198X"
]
],
"first_location_source": "inferred_birth_settlement",
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "Ben Pratten",
@ -108,7 +110,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/benpratten_20251214T103901Z.json"
],
"modified_at": "2026-01-09T19:18:18.987058+00:00",
"modified_at": "2026-01-09T19:51:31.857297+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "benpratten",
@ -121,6 +123,17 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_BEN-PRATTEN",
"new_ppid": "ID_AU-01-CAN_199X_AU-01-CAN_XXXX_BEN-PRATTEN",
"changed_at": "2026-01-09T19:51:31.857295+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -135,7 +148,7 @@
"primary_rationale": "1991 is in 199X, but range extends into 198X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_education_heuristic",
"inference_chain": [
{
"step": 1,
@ -184,7 +197,130 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 1991 spans decades 198X/199X",
"inferred_at": "2026-01-09T19:18:18.987022+00:00",
"inferred_at": "2026-01-09T19:51:31.814742+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_birth_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "low",
"inference_provenance": {
"method": "earliest_education_location",
"inference_chain": [
{
"step": 1,
"observation": "Earliest education institution identified",
"source_field": "profile_data.education",
"source_value": {
"institution": "The Australian National University",
"date_range": "2009 - 2009",
"degree": "Bachelor of Arts (B.A.) Honours, History"
}
},
{
"step": 2,
"lookup": "Institution location mapping",
"mapping_source": "DUTCH_UNI_LOCATIONS dictionary",
"mapping_key": "The Australian National University",
"mapping_result": "Canberra, Australia"
},
{
"step": 3,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australia",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 4,
"formatting": "CC-RR-PPP generation",
"components": {
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN"
},
"result": "AU-01-CAN"
}
],
"assumptions": [
"Student attended school near birth/family residence",
"Institution location is representative of early life location"
],
"assumption_note": "University location used as proxy for birth settlement; student may have relocated for education",
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:51:31.852337+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_current_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "medium",
"inference_provenance": {
"method": "profile_location",
"inference_chain": [
{
"step": 1,
"observation": "Profile location field found",
"source_field": "profile_data.location",
"source_value": "Canberra, Australian Capital Territory, Australia (AU)"
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australian Capital Territory, Australia (AU)",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"Profile location is up-to-date",
"Profile location represents current residence"
],
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:51:31.857284+00:00",
"inferred_by": "enrich_ppids.py"
}
}

148
data/person/ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_ISABELLE-SHEPPARD.json → data/person/ID_AU-01-CAN_199X_AU-01-CAN_XXXX_ISABELLE-SHEPPARD.json
View file

@ -1,11 +1,11 @@
{
"ppid": "ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_ISABELLE-SHEPPARD",
"ppid": "ID_AU-01-CAN_199X_AU-01-CAN_XXXX_ISABELLE-SHEPPARD",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-01-CAN",
"first_date": "199X",
"last_location": "XX-XX-XXX",
"last_location": "AU-01-CAN",
"last_date": "XXXX",
"name_tokens": [
"ISABELLE",
@ -14,7 +14,9 @@
"first_date_source": "inferred_birth_decade.primary_value",
"first_date_alternatives": [
"198X"
]
],
"first_location_source": "inferred_birth_settlement",
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "Isabelle Sheppard",
@ -164,7 +166,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/isabelle-sheppard-3ab30016b_20251214T104013Z.json"
],
"modified_at": "2026-01-09T19:18:13.621773+00:00",
"modified_at": "2026-01-09T19:50:55.218532+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "isabelle-sheppard-3ab30016b",
@ -177,6 +179,17 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_ISABELLE-SHEPPARD",
"new_ppid": "ID_AU-01-CAN_199X_AU-01-CAN_XXXX_ISABELLE-SHEPPARD",
"changed_at": "2026-01-09T19:50:55.218530+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -191,7 +204,7 @@
"primary_rationale": "1994 is in 199X, but range extends into 198X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_experience_heuristic",
"inference_chain": [
{
"step": 1,
@ -240,7 +253,128 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 1994 spans decades 198X/199X",
"inferred_at": "2026-01-09T19:18:13.621746+00:00",
"inferred_at": "2026-01-09T19:50:55.199364+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_birth_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_job_location",
"inference_chain": [
{
"step": 1,
"observation": "Earliest job with location found (no education location available)",
"source_field": "profile_data.experience",
"source_value": {
"company": "Ochre Health",
"title": "Medical Receptionist",
"date_range": "Mar 2017 - Oct 2021 • 4 years and 7 months",
"location": "Canberra, Australian Capital Territory, Australia"
}
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australian Capital Territory, Australia",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"First job location represents early life region"
],
"assumption_note": "Job location is weak proxy for birth location; person likely relocated for work",
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:50:55.204472+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_current_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "medium",
"inference_provenance": {
"method": "current_job_location",
"inference_chain": [
{
"step": 1,
"observation": "Profile location field found",
"source_field": "profile_data.location",
"source_value": "Hackett, Australian Capital Territory, Australia (AU)"
},
{
"step": 2,
"observation": "Current job with location found",
"source_field": "profile_data.experience",
"source_value": {
"company": "National Library of Australia",
"title": "Project Support Coordinator",
"location": "Canberra, Australian Capital Territory, Australia"
}
},
{
"step": 3,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australian Capital Territory, Australia",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 4,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"Current job location represents residence area",
"Person works near where they live"
],
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:50:55.218513+00:00",
"inferred_by": "enrich_ppids.py"
}
}

138
data/person/ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_JONATHAN-GREENSHAW.json → data/person/ID_AU-01-CAN_199X_AU-01-CAN_XXXX_JONATHAN-GREENSHAW.json
View file

@ -1,11 +1,11 @@
{
"ppid": "ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_JONATHAN-GREENSHAW",
"ppid": "ID_AU-01-CAN_199X_AU-01-CAN_XXXX_JONATHAN-GREENSHAW",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-01-CAN",
"first_date": "199X",
"last_location": "XX-XX-XXX",
"last_location": "AU-01-CAN",
"last_date": "XXXX",
"name_tokens": [
"JONATHAN",
@ -14,7 +14,9 @@
"first_date_source": "inferred_birth_decade.primary_value",
"first_date_alternatives": [
"198X"
]
],
"first_location_source": "inferred_birth_settlement",
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "Jonathan Greenshaw",
@ -87,7 +89,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/jonathan-greenshaw-928341113_20251214T103819Z.json"
],
"modified_at": "2026-01-09T19:18:14.285847+00:00",
"modified_at": "2026-01-09T19:50:59.856183+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "jonathan-greenshaw-928341113",
@ -100,6 +102,17 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_JONATHAN-GREENSHAW",
"new_ppid": "ID_AU-01-CAN_199X_AU-01-CAN_XXXX_JONATHAN-GREENSHAW",
"changed_at": "2026-01-09T19:50:59.856181+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -114,7 +127,7 @@
"primary_rationale": "1993 is in 199X, but range extends into 198X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_experience_heuristic",
"inference_chain": [
{
"step": 1,
@ -163,7 +176,118 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 1993 spans decades 198X/199X",
"inferred_at": "2026-01-09T19:18:14.285833+00:00",
"inferred_at": "2026-01-09T19:50:59.812305+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_birth_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_job_location",
"inference_chain": [
{
"step": 1,
"observation": "Earliest job with location found (no education location available)",
"source_field": "profile_data.experience",
"source_value": {
"company": "National Library of Australia",
"title": "System Administrator",
"date_range": "Apr 2016 - Jan 2023 • 6 years and 9 months",
"location": "Canberra, Australian Capital Territory, Australia"
}
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australian Capital Territory, Australia",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"First job location represents early life region"
],
"assumption_note": "Job location is weak proxy for birth location; person likely relocated for work",
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:50:59.851053+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_current_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "medium",
"inference_provenance": {
"method": "profile_location",
"inference_chain": [
{
"step": 1,
"observation": "Profile location field found",
"source_field": "profile_data.location",
"source_value": "Canberra, Australian Capital Territory, Australia (AU)"
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australian Capital Territory, Australia (AU)",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"Profile location is up-to-date",
"Profile location represents current residence"
],
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:50:59.856168+00:00",
"inferred_by": "enrich_ppids.py"
}
}

138
data/person/ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_KIM-BRUNORO.json → data/person/ID_AU-01-CAN_199X_AU-01-CAN_XXXX_KIM-BRUNORO.json
View file

@ -1,11 +1,11 @@
{
"ppid": "ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_KIM-BRUNORO",
"ppid": "ID_AU-01-CAN_199X_AU-01-CAN_XXXX_KIM-BRUNORO",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-01-CAN",
"first_date": "199X",
"last_location": "XX-XX-XXX",
"last_location": "AU-01-CAN",
"last_date": "XXXX",
"name_tokens": [
"KIM",
@ -14,7 +14,9 @@
"first_date_source": "inferred_birth_decade.primary_value",
"first_date_alternatives": [
"198X"
]
],
"first_location_source": "inferred_birth_settlement",
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "Kim Brunoro",
@ -92,7 +94,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/kim-brunoro-ab199a76_20251214T103936Z.json"
],
"modified_at": "2026-01-09T19:18:17.443396+00:00",
"modified_at": "2026-01-09T19:51:28.143574+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "kim-brunoro-ab199a76",
@ -105,6 +107,17 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_KIM-BRUNORO",
"new_ppid": "ID_AU-01-CAN_199X_AU-01-CAN_XXXX_KIM-BRUNORO",
"changed_at": "2026-01-09T19:51:28.143571+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -119,7 +132,7 @@
"primary_rationale": "1992 is in 199X, but range extends into 198X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_experience_heuristic",
"inference_chain": [
{
"step": 1,
@ -168,7 +181,118 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 1992 spans decades 198X/199X",
"inferred_at": "2026-01-09T19:18:17.443382+00:00",
"inferred_at": "2026-01-09T19:51:28.102556+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_birth_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_job_location",
"inference_chain": [
{
"step": 1,
"observation": "Earliest job with location found (no education location available)",
"source_field": "profile_data.experience",
"source_value": {
"company": "Department of Infrastructure, Transport, Regional Development and Communications",
"title": "Director",
"date_range": "Sep 2017 - Present • 6 years and 10 months",
"location": "Canberra, Australian Capital Territory, Australia"
}
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australian Capital Territory, Australia",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"First job location represents early life region"
],
"assumption_note": "Job location is weak proxy for birth location; person likely relocated for work",
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:51:28.137855+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_current_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "medium",
"inference_provenance": {
"method": "profile_location",
"inference_chain": [
{
"step": 1,
"observation": "Profile location field found",
"source_field": "profile_data.location",
"source_value": "Canberra, Australian Capital Territory, Australia (AU)"
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australian Capital Territory, Australia (AU)",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"Profile location is up-to-date",
"Profile location represents current residence"
],
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:51:28.143560+00:00",
"inferred_by": "enrich_ppids.py"
}
}

150
data/person/ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_MARJORIE-CURRIE.json → data/person/ID_AU-01-CAN_199X_AU-01-CAN_XXXX_MARJORIE-CURRIE.json
View file

@ -1,11 +1,11 @@
{
"ppid": "ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_MARJORIE-CURRIE",
"ppid": "ID_AU-01-CAN_199X_AU-01-CAN_XXXX_MARJORIE-CURRIE",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-01-CAN",
"first_date": "199X",
"last_location": "XX-XX-XXX",
"last_location": "AU-01-CAN",
"last_date": "XXXX",
"name_tokens": [
"MARJORIE",
@ -14,7 +14,9 @@
"first_date_source": "inferred_birth_decade.primary_value",
"first_date_alternatives": [
"198X"
]
],
"first_location_source": "inferred_birth_settlement",
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "Marjorie Currie",
@ -126,7 +128,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/marjorie-currie-a4b55a2b_20251214T104013Z.json"
],
"modified_at": "2026-01-09T19:18:17.021945+00:00",
"modified_at": "2026-01-09T19:51:22.980715+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "marjorie-currie-a4b55a2b",
@ -139,6 +141,17 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_MARJORIE-CURRIE",
"new_ppid": "ID_AU-01-CAN_199X_AU-01-CAN_XXXX_MARJORIE-CURRIE",
"changed_at": "2026-01-09T19:51:22.980713+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -153,7 +166,7 @@
"primary_rationale": "1992 is in 199X, but range extends into 198X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_education_heuristic",
"inference_chain": [
{
"step": 1,
@ -202,7 +215,130 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 1992 spans decades 198X/199X",
"inferred_at": "2026-01-09T19:18:17.021895+00:00",
"inferred_at": "2026-01-09T19:51:22.971004+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_birth_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "low",
"inference_provenance": {
"method": "earliest_education_location",
"inference_chain": [
{
"step": 1,
"observation": "Earliest education institution identified",
"source_field": "profile_data.education",
"source_value": {
"institution": "University of Canberra",
"date_range": "2010 - 2014 • 4 years",
"degree": "Bachelor of Cultural Heritage, Heritage, Museums and Conservation"
}
},
{
"step": 2,
"lookup": "Institution location mapping",
"mapping_source": "DUTCH_UNI_LOCATIONS dictionary",
"mapping_key": "University of Canberra",
"mapping_result": "Canberra, Australia"
},
{
"step": 3,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australia",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 4,
"formatting": "CC-RR-PPP generation",
"components": {
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN"
},
"result": "AU-01-CAN"
}
],
"assumptions": [
"Student attended school near birth/family residence",
"Institution location is representative of early life location"
],
"assumption_note": "University location used as proxy for birth settlement; student may have relocated for education",
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:51:22.975898+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_current_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "medium",
"inference_provenance": {
"method": "profile_location",
"inference_chain": [
{
"step": 1,
"observation": "Profile location field found",
"source_field": "profile_data.location",
"source_value": "Canberra, Australian Capital Territory, Australia (AU)"
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australian Capital Territory, Australia (AU)",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"Profile location is up-to-date",
"Profile location represents current residence"
],
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:51:22.980706+00:00",
"inferred_by": "enrich_ppids.py"
}
}

150
data/person/ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_ROSALIND-CLARKE.json → data/person/ID_AU-01-CAN_199X_AU-01-CAN_XXXX_ROSALIND-CLARKE.json
View file

@ -1,11 +1,11 @@
{
"ppid": "ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_ROSALIND-CLARKE",
"ppid": "ID_AU-01-CAN_199X_AU-01-CAN_XXXX_ROSALIND-CLARKE",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-01-CAN",
"first_date": "199X",
"last_location": "XX-XX-XXX",
"last_location": "AU-01-CAN",
"last_date": "XXXX",
"name_tokens": [
"ROSALIND",
@ -14,7 +14,9 @@
"first_date_source": "inferred_birth_decade.primary_value",
"first_date_alternatives": [
"198X"
]
],
"first_location_source": "inferred_birth_settlement",
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "Rosalind Clarke",
@ -156,7 +158,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/rosalindclarke378_20251214T103906Z.json"
],
"modified_at": "2026-01-09T19:18:15.171238+00:00",
"modified_at": "2026-01-09T19:51:06.987046+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "rosalindclarke378",
@ -169,6 +171,17 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_ROSALIND-CLARKE",
"new_ppid": "ID_AU-01-CAN_199X_AU-01-CAN_XXXX_ROSALIND-CLARKE",
"changed_at": "2026-01-09T19:51:06.987044+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -183,7 +196,7 @@
"primary_rationale": "1991 is in 199X, but range extends into 198X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_education_heuristic",
"inference_chain": [
{
"step": 1,
@ -232,7 +245,130 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 1991 spans decades 198X/199X",
"inferred_at": "2026-01-09T19:18:15.171188+00:00",
"inferred_at": "2026-01-09T19:51:06.977077+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_birth_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "low",
"inference_provenance": {
"method": "earliest_education_location",
"inference_chain": [
{
"step": 1,
"observation": "Earliest education institution identified",
"source_field": "profile_data.education",
"source_value": {
"institution": "The Australian National University",
"date_range": "2013 - 2014 • 1 year",
"degree": "Masters of Liberal Arts (Museums and Collections), Museology/Museum Studies"
}
},
{
"step": 2,
"lookup": "Institution location mapping",
"mapping_source": "DUTCH_UNI_LOCATIONS dictionary",
"mapping_key": "The Australian National University",
"mapping_result": "Canberra, Australia"
},
{
"step": 3,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australia",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 4,
"formatting": "CC-RR-PPP generation",
"components": {
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN"
},
"result": "AU-01-CAN"
}
],
"assumptions": [
"Student attended school near birth/family residence",
"Institution location is representative of early life location"
],
"assumption_note": "University location used as proxy for birth settlement; student may have relocated for education",
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:51:06.982311+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_current_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "medium",
"inference_provenance": {
"method": "profile_location",
"inference_chain": [
{
"step": 1,
"observation": "Profile location field found",
"source_field": "profile_data.location",
"source_value": "Canberra, Australian Capital Territory, Australia (AU)"
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australian Capital Territory, Australia (AU)",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"Profile location is up-to-date",
"Profile location represents current residence"
],
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:51:06.987037+00:00",
"inferred_by": "enrich_ppids.py"
}
}

150
data/person/ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_SARAH-HODGE.json → data/person/ID_AU-01-CAN_199X_AU-01-CAN_XXXX_SARAH-HODGE.json
View file

@ -1,11 +1,11 @@
{
"ppid": "ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_SARAH-HODGE",
"ppid": "ID_AU-01-CAN_199X_AU-01-CAN_XXXX_SARAH-HODGE",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-01-CAN",
"first_date": "199X",
"last_location": "XX-XX-XXX",
"last_location": "AU-01-CAN",
"last_date": "XXXX",
"name_tokens": [
"SARAH",
@ -14,7 +14,9 @@
"first_date_source": "inferred_birth_decade",
"first_date_alternatives": [
"199X"
]
],
"first_location_source": "inferred_birth_settlement",
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "Sarah Hodge",
@ -92,7 +94,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/sarah-hodge-8484791aa_20251214T103847Z.json"
],
"modified_at": "2026-01-09T19:18:16.603584+00:00",
"modified_at": "2026-01-09T19:50:58.594474+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "sarah-hodge-8484791aa",
@ -114,6 +116,17 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_SARAH-HODGE",
"new_ppid": "ID_AU-01-CAN_199X_AU-01-CAN_XXXX_SARAH-HODGE",
"changed_at": "2026-01-09T19:50:58.594466+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -122,7 +135,7 @@
"precision": "decade",
"confidence": "low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_education_heuristic",
"inference_chain": [
{
"step": 1,
@ -163,7 +176,130 @@
"Entry age for education/first job: 24 years (±3)",
"Career records are complete in LinkedIn profile"
],
"inferred_at": "2026-01-09T19:18:16.603553+00:00",
"inferred_at": "2026-01-09T19:50:58.576353+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_birth_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "low",
"inference_provenance": {
"method": "earliest_education_location",
"inference_chain": [
{
"step": 1,
"observation": "Earliest education institution identified",
"source_field": "profile_data.education",
"source_value": {
"institution": "The Australian National University",
"date_range": "2020 - 2024 • 4 years",
"degree": "Doctor of Philosophy - PhD"
}
},
{
"step": 2,
"lookup": "Institution location mapping",
"mapping_source": "DUTCH_UNI_LOCATIONS dictionary",
"mapping_key": "The Australian National University",
"mapping_result": "Canberra, Australia"
},
{
"step": 3,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australia",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 4,
"formatting": "CC-RR-PPP generation",
"components": {
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN"
},
"result": "AU-01-CAN"
}
],
"assumptions": [
"Student attended school near birth/family residence",
"Institution location is representative of early life location"
],
"assumption_note": "University location used as proxy for birth settlement; student may have relocated for education",
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:50:58.584222+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_current_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "medium",
"inference_provenance": {
"method": "profile_location",
"inference_chain": [
{
"step": 1,
"observation": "Profile location field found",
"source_field": "profile_data.location",
"source_value": "Canberra, Australian Capital Territory, Australia (AU)"
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australian Capital Territory, Australia (AU)",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"Profile location is up-to-date",
"Profile location represents current residence"
],
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:50:58.594438+00:00",
"inferred_by": "enrich_ppids.py"
}
}

138
data/person/ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_SONJA-B.json → data/person/ID_AU-01-CAN_199X_AU-01-CAN_XXXX_SONJA-B.json
View file

@ -1,11 +1,11 @@
{
"ppid": "ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_SONJA-B",
"ppid": "ID_AU-01-CAN_199X_AU-01-CAN_XXXX_SONJA-B",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-01-CAN",
"first_date": "199X",
"last_location": "XX-XX-XXX",
"last_location": "AU-01-CAN",
"last_date": "XXXX",
"name_tokens": [
"SONJA",
@ -14,7 +14,9 @@
"first_date_source": "inferred_birth_decade.primary_value",
"first_date_alternatives": [
"200X"
]
],
"first_location_source": "inferred_birth_settlement",
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "Sonja B.",
@ -83,7 +85,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/sonjabarfoed_20251214T103926Z.json"
],
"modified_at": "2026-01-09T19:18:12.796539+00:00",
"modified_at": "2026-01-09T19:50:48.893435+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "sonjabarfoed",
@ -96,6 +98,17 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_SONJA-B",
"new_ppid": "ID_AU-01-CAN_199X_AU-01-CAN_XXXX_SONJA-B",
"changed_at": "2026-01-09T19:50:48.893432+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -110,7 +123,7 @@
"primary_rationale": "1997 is in 199X, but range extends into 200X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_experience_heuristic",
"inference_chain": [
{
"step": 1,
@ -159,7 +172,118 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 1997 spans decades 199X/200X",
"inferred_at": "2026-01-09T19:18:12.796511+00:00",
"inferred_at": "2026-01-09T19:50:48.880237+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_birth_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_job_location",
"inference_chain": [
{
"step": 1,
"observation": "Earliest job with location found (no education location available)",
"source_field": "profile_data.experience",
"source_value": {
"company": "National Library of Australia",
"title": "Co-ordinator Out Of Hours Operations (part-time After-hours)",
"date_range": "Nov 2020 - Present • 5 years",
"location": "Canberra, Australian Capital Territory, Australia"
}
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australian Capital Territory, Australia",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"First job location represents early life region"
],
"assumption_note": "Job location is weak proxy for birth location; person likely relocated for work",
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:50:48.885443+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_current_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "medium",
"inference_provenance": {
"method": "profile_location",
"inference_chain": [
{
"step": 1,
"observation": "Profile location field found",
"source_field": "profile_data.location",
"source_value": "Canberra, Australian Capital Territory, Australia (AU)"
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australian Capital Territory, Australia (AU)",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"Profile location is up-to-date",
"Profile location represents current residence"
],
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:50:48.893415+00:00",
"inferred_by": "enrich_ppids.py"
}
}

150
data/person/ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_CELIA-RIDEAUX.json → data/person/ID_AU-01-CAN_199X_AU-04-COO_XXXX_CELIA-RIDEAUX.json
View file

@ -1,11 +1,11 @@
{
"ppid": "ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_CELIA-RIDEAUX",
"ppid": "ID_AU-01-CAN_199X_AU-04-COO_XXXX_CELIA-RIDEAUX",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-01-CAN",
"first_date": "199X",
"last_location": "XX-XX-XXX",
"last_location": "AU-04-COO",
"last_date": "XXXX",
"name_tokens": [
"CELIA",
@ -14,7 +14,9 @@
"first_date_source": "inferred_birth_decade.primary_value",
"first_date_alternatives": [
"198X"
]
],
"first_location_source": "inferred_birth_settlement",
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "Celia Rideaux",
@ -179,7 +181,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/celia-rideaux-3867b94a_20251214T103844Z.json"
],
"modified_at": "2026-01-09T19:18:16.186785+00:00",
"modified_at": "2026-01-09T19:51:18.267551+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "celia-rideaux-3867b94a",
@ -192,6 +194,17 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_CELIA-RIDEAUX",
"new_ppid": "ID_AU-01-CAN_199X_AU-04-COO_XXXX_CELIA-RIDEAUX",
"changed_at": "2026-01-09T19:51:18.267549+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -206,7 +219,7 @@
"primary_rationale": "1992 is in 199X, but range extends into 198X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_education_heuristic",
"inference_chain": [
{
"step": 1,
@ -255,7 +268,130 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 1992 spans decades 198X/199X",
"inferred_at": "2026-01-09T19:18:16.186725+00:00",
"inferred_at": "2026-01-09T19:51:18.256026+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_birth_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "low",
"inference_provenance": {
"method": "earliest_education_location",
"inference_chain": [
{
"step": 1,
"observation": "Earliest education institution identified",
"source_field": "profile_data.education",
"source_value": {
"institution": "University of Canberra",
"date_range": "2010 - 2012 • 2 years",
"degree": "Bachelor of Public Relations, Public Relations"
}
},
{
"step": 2,
"lookup": "Institution location mapping",
"mapping_source": "DUTCH_UNI_LOCATIONS dictionary",
"mapping_key": "University of Canberra",
"mapping_result": "Canberra, Australia"
},
{
"step": 3,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australia",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 4,
"formatting": "CC-RR-PPP generation",
"components": {
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN"
},
"result": "AU-01-CAN"
}
],
"assumptions": [
"Student attended school near birth/family residence",
"Institution location is representative of early life location"
],
"assumption_note": "University location used as proxy for birth settlement; student may have relocated for education",
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:51:18.261855+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_current_settlement": {
"value": "Cooktown",
"formatted": "AU-04-COO",
"country_code": "AU",
"region_code": "04",
"settlement_code": "COO",
"confidence": "medium",
"inference_provenance": {
"method": "profile_location",
"inference_chain": [
{
"step": 1,
"observation": "Profile location field found",
"source_field": "profile_data.location",
"source_value": "Cook, Australian Capital Territory, Australia (AU)"
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Cook, Australian Capital Territory, Australia (AU)",
"result": {
"geonames_id": 2170658,
"geonames_name": "Cooktown",
"admin1_code": "04",
"admin1_name": "Queensland",
"feature_code": "PPL",
"latitude": -15.4657,
"longitude": 145.24984
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-04-COO"
}
],
"assumptions": [
"Profile location is up-to-date",
"Profile location represents current residence"
],
"geonames_data": {
"geonames_id": 2170658,
"geonames_name": "Cooktown",
"admin1_code": "04",
"admin1_name": "Queensland",
"feature_code": "PPL",
"latitude": -15.4657,
"longitude": 145.24984
},
"inferred_at": "2026-01-09T19:51:18.267538+00:00",
"inferred_by": "enrich_ppids.py"
}
}

171
data/person/ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_JENNIFER-THOMPSON.json → data/person/ID_AU-01-CAN_199X_AU-05-AP_XXXX_JENNIFER-THOMPSON.json
View file

@ -1,11 +1,11 @@
{
"ppid": "ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_JENNIFER-THOMPSON",
"ppid": "ID_AU-01-CAN_199X_AU-05-AP_XXXX_JENNIFER-THOMPSON",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-01-CAN",
"first_date": "199X",
"last_location": "XX-XX-XXX",
"last_location": "AU-05-AP",
"last_date": "XXXX",
"name_tokens": [
"JENNIFER",
@ -14,7 +14,9 @@
"first_date_source": "inferred_birth_decade.primary_value",
"first_date_alternatives": [
"198X"
]
],
"first_location_source": "inferred_birth_settlement",
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "Jennifer Thompson",
@ -218,7 +220,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/jenthompson2020_20251214T103818Z.json"
],
"modified_at": "2026-01-09T19:18:15.534360+00:00",
"modified_at": "2026-01-09T19:50:50.786088+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "jenthompson2020",
@ -240,6 +242,17 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_JENNIFER-THOMPSON",
"new_ppid": "ID_AU-01-CAN_199X_AU-05-AP_XXXX_JENNIFER-THOMPSON",
"changed_at": "2026-01-09T19:50:50.786085+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -254,7 +267,7 @@
"primary_rationale": "1990 is in 199X, but range extends into 198X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_education_heuristic",
"inference_chain": [
{
"step": 1,
@ -303,7 +316,151 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 1990 spans decades 198X/199X",
"inferred_at": "2026-01-09T19:18:15.534248+00:00",
"inferred_at": "2026-01-09T19:50:50.624376+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_birth_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_job_location",
"inference_chain": [
{
"step": 1,
"observation": "Earliest job with location found (no education location available)",
"source_field": "profile_data.experience",
"source_value": {
"company": "RMK Voice Productions",
"title": "Casting Agent",
"date_range": "Jan 1994 - Jan 1995 • 1 year",
"location": "Sydney, New South Wales, Australia"
}
},
{
"step": 2,
"observation": "Earliest job with location found (no education location available)",
"source_field": "profile_data.experience",
"source_value": {
"company": "Labsonics",
"title": "Sound Studio Coordinator",
"date_range": "Jan 1999 - Jan 1999",
"location": "Sydney, New South Wales, Australia"
}
},
{
"step": 3,
"observation": "Earliest job with location found (no education location available)",
"source_field": "profile_data.experience",
"source_value": {
"company": "Kids Like Us Productions",
"title": "Production Producer's Assistant, Hi-5 TV Series, Videos And Live Performance",
"date_range": "Jan 1999 - Jan 1999",
"location": "Sydney, New South Wales, Australia"
}
},
{
"step": 4,
"observation": "Earliest job with location found (no education location available)",
"source_field": "profile_data.experience",
"source_value": {
"company": "National Film and Sound Archive of Australia",
"title": "Various",
"date_range": "Collection Development - Oral History (2000-2002) Collection Preservation - Sound (2002-2004) Collection Access (2004-2006)",
"location": "Canberra, Australian Capital Territory, Australia"
}
},
{
"step": 5,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australian Capital Territory, Australia",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 6,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"First job location represents early life region"
],
"assumption_note": "Job location is weak proxy for birth location; person likely relocated for work",
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:50:50.780942+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_current_settlement": {
"value": "Australia Plains",
"formatted": "AU-05-AP",
"country_code": "AU",
"region_code": "05",
"settlement_code": "AP",
"confidence": "medium",
"inference_provenance": {
"method": "profile_location",
"inference_chain": [
{
"step": 1,
"observation": "Profile location field found",
"source_field": "profile_data.location",
"source_value": "Australia (AU)"
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Australia (AU)",
"result": {
"geonames_id": 2077455,
"geonames_name": "Australia Plains",
"admin1_code": "05",
"admin1_name": "South Australia",
"feature_code": "PPL",
"latitude": -34.09703,
"longitude": 139.15616
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-05-AP"
}
],
"assumptions": [
"Profile location is up-to-date",
"Profile location represents current residence"
],
"geonames_data": {
"geonames_id": 2077455,
"geonames_name": "Australia Plains",
"admin1_code": "05",
"admin1_name": "South Australia",
"feature_code": "PPL",
"latitude": -34.09703,
"longitude": 139.15616
},
"inferred_at": "2026-01-09T19:50:50.786071+00:00",
"inferred_by": "enrich_ppids.py"
}
}

150
data/person/ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_MIRIAM-COVELL.json → data/person/ID_AU-01-CAN_199X_AU-05-AP_XXXX_MIRIAM-COVELL.json
View file

@ -1,17 +1,19 @@
{
"ppid": "ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_MIRIAM-COVELL",
"ppid": "ID_AU-01-CAN_199X_AU-05-AP_XXXX_MIRIAM-COVELL",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-01-CAN",
"first_date": "199X",
"last_location": "XX-XX-XXX",
"last_location": "AU-05-AP",
"last_date": "XXXX",
"name_tokens": [
"MIRIAM",
"COVELL"
],
"first_date_source": "inferred_birth_decade"
"first_date_source": "inferred_birth_decade",
"first_location_source": "inferred_birth_settlement",
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "Miriam Covell",
@ -131,7 +133,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/miriam-covell-8b2515165_20251214T103846Z.json"
],
"modified_at": "2026-01-09T19:18:13.460463+00:00",
"modified_at": "2026-01-09T19:50:54.475860+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "miriam-covell-8b2515165",
@ -144,6 +146,17 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_MIRIAM-COVELL",
"new_ppid": "ID_AU-01-CAN_199X_AU-05-AP_XXXX_MIRIAM-COVELL",
"changed_at": "2026-01-09T19:50:54.475858+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -152,7 +165,7 @@
"precision": "decade",
"confidence": "low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_education_heuristic",
"inference_chain": [
{
"step": 1,
@ -193,7 +206,130 @@
"Entry age for education/first job: 18 years (±3)",
"Career records are complete in LinkedIn profile"
],
"inferred_at": "2026-01-09T19:18:13.460418+00:00",
"inferred_at": "2026-01-09T19:50:54.464352+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_birth_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "low",
"inference_provenance": {
"method": "earliest_education_location",
"inference_chain": [
{
"step": 1,
"observation": "Earliest education institution identified",
"source_field": "profile_data.education",
"source_value": {
"institution": "The Australian National University",
"date_range": "2014 - 2018 • 4 years",
"degree": "Bachelor of Arts (Honours), HISTORY"
}
},
{
"step": 2,
"lookup": "Institution location mapping",
"mapping_source": "DUTCH_UNI_LOCATIONS dictionary",
"mapping_key": "The Australian National University",
"mapping_result": "Canberra, Australia"
},
{
"step": 3,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australia",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 4,
"formatting": "CC-RR-PPP generation",
"components": {
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN"
},
"result": "AU-01-CAN"
}
],
"assumptions": [
"Student attended school near birth/family residence",
"Institution location is representative of early life location"
],
"assumption_note": "University location used as proxy for birth settlement; student may have relocated for education",
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:50:54.470591+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_current_settlement": {
"value": "Australia Plains",
"formatted": "AU-05-AP",
"country_code": "AU",
"region_code": "05",
"settlement_code": "AP",
"confidence": "medium",
"inference_provenance": {
"method": "profile_location",
"inference_chain": [
{
"step": 1,
"observation": "Profile location field found",
"source_field": "profile_data.location",
"source_value": "Australia (AU)"
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Australia (AU)",
"result": {
"geonames_id": 2077455,
"geonames_name": "Australia Plains",
"admin1_code": "05",
"admin1_name": "South Australia",
"feature_code": "PPL",
"latitude": -34.09703,
"longitude": 139.15616
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-05-AP"
}
],
"assumptions": [
"Profile location is up-to-date",
"Profile location represents current residence"
],
"geonames_data": {
"geonames_id": 2077455,
"geonames_name": "Australia Plains",
"admin1_code": "05",
"admin1_name": "South Australia",
"feature_code": "PPL",
"latitude": -34.09703,
"longitude": 139.15616
},
"inferred_at": "2026-01-09T19:50:54.475849+00:00",
"inferred_by": "enrich_ppids.py"
}
}

27
data/person/ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_QIANMIN-JIA.json → data/person/ID_AU-01-CAN_199X_AU-05-AP_XXXX_QIANMIN-JIA.json
View file

@ -1,11 +1,11 @@
{
"ppid": "ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_QIANMIN-JIA",
"ppid": "ID_AU-01-CAN_199X_AU-05-AP_XXXX_QIANMIN-JIA",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-01-CAN",
"first_date": "199X",
"last_location": "XX-XX-XXX",
"last_location": "AU-05-AP",
"last_date": "XXXX",
"name_tokens": [
"QIANMIN",
@ -14,7 +14,9 @@
"first_date_source": "inferred_birth_decade.primary_value",
"first_date_alternatives": [
"198X"
]
],
"first_location_source": "inferred_birth_settlement",
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "Qianmin Jia",
@ -108,7 +110,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/qianmin-min-jia-35b1311a4_20251214T103821Z.json"
],
"modified_at": "2026-01-09T19:18:11.315676+00:00",
"modified_at": "2026-01-09T19:51:03.395295+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "qianmin-min-jia-35b1311a4",
@ -121,6 +123,17 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_QIANMIN-JIA",
"new_ppid": "ID_AU-01-CAN_199X_AU-05-AP_XXXX_QIANMIN-JIA",
"changed_at": "2026-01-09T19:47:58.182271+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -135,7 +148,7 @@
"primary_rationale": "1993 is in 199X, but range extends into 198X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_experience_heuristic",
"inference_chain": [
{
"step": 1,
@ -184,7 +197,7 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 1993 spans decades 198X/199X",
"inferred_at": "2026-01-09T19:18:11.315654+00:00",
"inferred_at": "2026-01-09T19:51:03.395289+00:00",
"inferred_by": "enrich_ppids.py"
}
}

138
data/person/ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_ROS-H.json → data/person/ID_AU-01-CAN_199X_AU-05-AP_XXXX_ROS-H.json
View file

@ -1,11 +1,11 @@
{
"ppid": "ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_ROS-H",
"ppid": "ID_AU-01-CAN_199X_AU-05-AP_XXXX_ROS-H",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-01-CAN",
"first_date": "199X",
"last_location": "XX-XX-XXX",
"last_location": "AU-05-AP",
"last_date": "XXXX",
"name_tokens": [
"ROS",
@ -14,7 +14,9 @@
"first_date_source": "inferred_birth_decade.primary_value",
"first_date_alternatives": [
"198X"
]
],
"first_location_source": "inferred_birth_settlement",
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "Ros H.",
@ -139,7 +141,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/ros-h-1b870856_20251214T103751Z.json"
],
"modified_at": "2026-01-09T19:18:13.553731+00:00",
"modified_at": "2026-01-09T19:50:54.649564+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "ros-h-1b870856",
@ -152,6 +154,17 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_ROS-H",
"new_ppid": "ID_AU-01-CAN_199X_AU-05-AP_XXXX_ROS-H",
"changed_at": "2026-01-09T19:50:54.649562+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -166,7 +179,7 @@
"primary_rationale": "1990 is in 199X, but range extends into 198X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_experience_heuristic",
"inference_chain": [
{
"step": 1,
@ -215,7 +228,118 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 1990 spans decades 198X/199X",
"inferred_at": "2026-01-09T19:18:13.553708+00:00",
"inferred_at": "2026-01-09T19:50:54.630524+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_birth_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_job_location",
"inference_chain": [
{
"step": 1,
"observation": "Earliest job with location found (no education location available)",
"source_field": "profile_data.experience",
"source_value": {
"company": "National Library of Australia",
"title": "Australian And Overseas Monographs - Cataloguer",
"date_range": "Jan 2014 - Apr 2015 • 1 year and 3 months",
"location": "Canberra, Australia"
}
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australia",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"First job location represents early life region"
],
"assumption_note": "Job location is weak proxy for birth location; person likely relocated for work",
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:50:54.635474+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_current_settlement": {
"value": "Australia Plains",
"formatted": "AU-05-AP",
"country_code": "AU",
"region_code": "05",
"settlement_code": "AP",
"confidence": "medium",
"inference_provenance": {
"method": "profile_location",
"inference_chain": [
{
"step": 1,
"observation": "Profile location field found",
"source_field": "profile_data.location",
"source_value": "Australia (AU)"
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Australia (AU)",
"result": {
"geonames_id": 2077455,
"geonames_name": "Australia Plains",
"admin1_code": "05",
"admin1_name": "South Australia",
"feature_code": "PPL",
"latitude": -34.09703,
"longitude": 139.15616
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-05-AP"
}
],
"assumptions": [
"Profile location is up-to-date",
"Profile location represents current residence"
],
"geonames_data": {
"geonames_id": 2077455,
"geonames_name": "Australia Plains",
"admin1_code": "05",
"admin1_name": "South Australia",
"feature_code": "PPL",
"latitude": -34.09703,
"longitude": 139.15616
},
"inferred_at": "2026-01-09T19:50:54.649545+00:00",
"inferred_by": "enrich_ppids.py"
}
}

138
data/person/ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_MADELINE-ONEIL.json → data/person/ID_AU-01-CAN_199X_AU-07-FLY_XXXX_MADELINE-ONEIL.json
View file

@ -1,11 +1,11 @@
{
"ppid": "ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_MADELINE-ONEIL",
"ppid": "ID_AU-01-CAN_199X_AU-07-FLY_XXXX_MADELINE-ONEIL",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-01-CAN",
"first_date": "199X",
"last_location": "XX-XX-XXX",
"last_location": "AU-07-FLY",
"last_date": "XXXX",
"name_tokens": [
"MADELINE",
@ -14,7 +14,9 @@
"first_date_source": "inferred_birth_decade.primary_value",
"first_date_alternatives": [
"200X"
]
],
"first_location_source": "inferred_birth_settlement",
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "Madeline O'Neil",
@ -135,7 +137,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/madeline-o-neil-14b714264_20251214T103819Z.json"
],
"modified_at": "2026-01-09T19:18:14.634599+00:00",
"modified_at": "2026-01-09T19:51:03.206334+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "madeline-o-neil-14b714264",
@ -148,6 +150,17 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_MADELINE-ONEIL",
"new_ppid": "ID_AU-01-CAN_199X_AU-07-FLY_XXXX_MADELINE-ONEIL",
"changed_at": "2026-01-09T19:51:03.206331+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -162,7 +175,7 @@
"primary_rationale": "1998 is in 199X, but range extends into 200X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_experience_heuristic",
"inference_chain": [
{
"step": 1,
@ -211,7 +224,118 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 1998 spans decades 199X/200X",
"inferred_at": "2026-01-09T19:18:14.634563+00:00",
"inferred_at": "2026-01-09T19:51:03.194185+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_birth_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_job_location",
"inference_chain": [
{
"step": 1,
"observation": "Earliest job with location found (no education location available)",
"source_field": "profile_data.experience",
"source_value": {
"company": "Australian War Memorial",
"title": "Education Assistant",
"date_range": "Mar 2021 - Jun 2023 • 2 years and 3 months",
"location": "Canberra, Australian Capital Territory, Australia"
}
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australian Capital Territory, Australia",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"First job location represents early life region"
],
"assumption_note": "Job location is weak proxy for birth location; person likely relocated for work",
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:51:03.201179+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_current_settlement": {
"value": "Flynn",
"formatted": "AU-07-FLY",
"country_code": "AU",
"region_code": "07",
"settlement_code": "FLY",
"confidence": "medium",
"inference_provenance": {
"method": "profile_location",
"inference_chain": [
{
"step": 1,
"observation": "Profile location field found",
"source_field": "profile_data.location",
"source_value": "Flynn, Australian Capital Territory, Australia (AU)"
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Flynn, Australian Capital Territory, Australia (AU)",
"result": {
"geonames_id": 2166389,
"geonames_name": "Flynn",
"admin1_code": "07",
"admin1_name": "Victoria",
"feature_code": "PPL",
"latitude": -38.16667,
"longitude": 146.68333
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-07-FLY"
}
],
"assumptions": [
"Profile location is up-to-date",
"Profile location represents current residence"
],
"geonames_data": {
"geonames_id": 2166389,
"geonames_name": "Flynn",
"admin1_code": "07",
"admin1_name": "Victoria",
"feature_code": "PPL",
"latitude": -38.16667,
"longitude": 146.68333
},
"inferred_at": "2026-01-09T19:51:03.206321+00:00",
"inferred_by": "enrich_ppids.py"
}
}

150
data/person/ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_MAYUKH-DIKSHIT.json → data/person/ID_AU-01-CAN_199X_AU-08-SB_XXXX_MAYUKH-DIKSHIT.json
View file

@ -1,11 +1,11 @@
{
"ppid": "ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_MAYUKH-DIKSHIT",
"ppid": "ID_AU-01-CAN_199X_AU-08-SB_XXXX_MAYUKH-DIKSHIT",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-01-CAN",
"first_date": "199X",
"last_location": "XX-XX-XXX",
"last_location": "AU-08-SB",
"last_date": "XXXX",
"name_tokens": [
"MAYUKH",
@ -14,7 +14,9 @@
"first_date_source": "inferred_birth_decade.primary_value",
"first_date_alternatives": [
"200X"
]
],
"first_location_source": "inferred_birth_settlement",
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "Mayukh Dikshit",
@ -254,7 +256,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/mayukh-dikshit-2b03ba117_20251214T103849Z.json"
],
"modified_at": "2026-01-09T19:18:15.077117+00:00",
"modified_at": "2026-01-09T19:51:06.698138+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "mayukh-dikshit-2b03ba117",
@ -267,6 +269,17 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_MAYUKH-DIKSHIT",
"new_ppid": "ID_AU-01-CAN_199X_AU-08-SB_XXXX_MAYUKH-DIKSHIT",
"changed_at": "2026-01-09T19:51:06.698135+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -281,7 +294,7 @@
"primary_rationale": "1998 is in 199X, but range extends into 200X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_education_heuristic",
"inference_chain": [
{
"step": 1,
@ -330,7 +343,130 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 1998 spans decades 199X/200X",
"inferred_at": "2026-01-09T19:18:15.077070+00:00",
"inferred_at": "2026-01-09T19:51:06.684469+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_birth_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "low",
"inference_provenance": {
"method": "earliest_education_location",
"inference_chain": [
{
"step": 1,
"observation": "Earliest education institution identified",
"source_field": "profile_data.education",
"source_value": {
"institution": "The Australian National University",
"date_range": "2016 - 2018 • 2 years",
"degree": "MBA"
}
},
{
"step": 2,
"lookup": "Institution location mapping",
"mapping_source": "DUTCH_UNI_LOCATIONS dictionary",
"mapping_key": "The Australian National University",
"mapping_result": "Canberra, Australia"
},
{
"step": 3,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australia",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 4,
"formatting": "CC-RR-PPP generation",
"components": {
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN"
},
"result": "AU-01-CAN"
}
],
"assumptions": [
"Student attended school near birth/family residence",
"Institution location is representative of early life location"
],
"assumption_note": "University location used as proxy for birth settlement; student may have relocated for education",
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:51:06.690773+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_current_settlement": {
"value": "Spencers Brook",
"formatted": "AU-08-SB",
"country_code": "AU",
"region_code": "08",
"settlement_code": "SB",
"confidence": "medium",
"inference_provenance": {
"method": "profile_location",
"inference_chain": [
{
"step": 1,
"observation": "Profile location field found",
"source_field": "profile_data.location",
"source_value": "Spence, Australian Capital Territory, Australia (AU)"
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Spence, Australian Capital Territory, Australia (AU)",
"result": {
"geonames_id": 2061211,
"geonames_name": "Spencers Brook",
"admin1_code": "08",
"admin1_name": "Western Australia",
"feature_code": "PPL",
"latitude": -31.73655,
"longitude": 116.6306
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-08-SB"
}
],
"assumptions": [
"Profile location is up-to-date",
"Profile location represents current residence"
],
"geonames_data": {
"geonames_id": 2061211,
"geonames_name": "Spencers Brook",
"admin1_code": "08",
"admin1_name": "Western Australia",
"feature_code": "PPL",
"latitude": -31.73655,
"longitude": 116.6306
},
"inferred_at": "2026-01-09T19:51:06.698122+00:00",
"inferred_by": "enrich_ppids.py"
}
}

81
data/person/ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_BEN-STEVENS.json → data/person/ID_AU-01-CAN_199X_XX-XX-XXX_XXXX_BEN-STEVENS.json
View file

@ -1,9 +1,9 @@
{
"ppid": "ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_BEN-STEVENS",
"ppid": "ID_AU-01-CAN_199X_XX-XX-XXX_XXXX_BEN-STEVENS",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-01-CAN",
"first_date": "199X",
"last_location": "XX-XX-XXX",
"last_date": "XXXX",
@ -14,7 +14,8 @@
"first_date_source": "inferred_birth_decade.primary_value",
"first_date_alternatives": [
"200X"
]
],
"first_location_source": "inferred_birth_settlement"
},
"name": {
"full_name": "Ben Stevens",
@ -98,7 +99,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/ben-stevens-b0a254246_20251214T103814Z.json"
],
"modified_at": "2026-01-09T19:18:14.994277+00:00",
"modified_at": "2026-01-09T19:51:06.565754+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "ben-stevens-b0a254246",
@ -111,6 +112,16 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_BEN-STEVENS",
"new_ppid": "ID_AU-01-CAN_199X_XX-XX-XXX_XXXX_BEN-STEVENS",
"changed_at": "2026-01-09T19:51:06.565735+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement"
]
}
],
"inferred_birth_decade": {
@ -125,7 +136,7 @@
"primary_rationale": "1995 is in 199X, but range extends into 200X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_experience_heuristic",
"inference_chain": [
{
"step": 1,
@ -174,7 +185,65 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 1995 spans decades 199X/200X",
"inferred_at": "2026-01-09T19:18:14.994261+00:00",
"inferred_at": "2026-01-09T19:51:06.508306+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_birth_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_job_location",
"inference_chain": [
{
"step": 1,
"observation": "Earliest job with location found (no education location available)",
"source_field": "profile_data.experience",
"source_value": {
"company": "Interaction Consulting Group",
"title": "Executive Assistant RTO Admin",
"date_range": "Sep 2022 - Jul 2023 • 10 months",
"location": "Canberra, Australian Capital Territory, Australia"
}
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australian Capital Territory, Australia",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"First job location represents early life region"
],
"assumption_note": "Job location is weak proxy for birth location; person likely relocated for work",
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:51:06.514616+00:00",
"inferred_by": "enrich_ppids.py"
}
}

23
data/person/ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_JACKY-YANG.json → data/person/ID_AU-01-CAN_199X_XX-XX-XXX_XXXX_JACKY-YANG.json
View file

@ -1,9 +1,9 @@
{
"ppid": "ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_JACKY-YANG",
"ppid": "ID_AU-01-CAN_199X_XX-XX-XXX_XXXX_JACKY-YANG",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-01-CAN",
"first_date": "199X",
"last_location": "XX-XX-XXX",
"last_date": "XXXX",
@ -14,7 +14,8 @@
"first_date_source": "inferred_birth_decade.primary_value",
"first_date_alternatives": [
"198X"
]
],
"first_location_source": "inferred_birth_settlement"
},
"name": {
"full_name": "Jacky YANG",
@ -194,7 +195,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/jacky-yang-009997149_20251214T103928Z.json"
],
"modified_at": "2026-01-09T19:18:11.317309+00:00",
"modified_at": "2026-01-09T19:51:08.562053+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "jacky-yang-009997149",
@ -207,6 +208,16 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_JACKY-YANG",
"new_ppid": "ID_AU-01-CAN_199X_XX-XX-XXX_XXXX_JACKY-YANG",
"changed_at": "2026-01-09T19:47:58.195085+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement"
]
}
],
"inferred_birth_decade": {
@ -221,7 +232,7 @@
"primary_rationale": "1990 is in 199X, but range extends into 198X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_education_heuristic",
"inference_chain": [
{
"step": 1,
@ -270,7 +281,7 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 1990 spans decades 198X/199X",
"inferred_at": "2026-01-09T19:18:11.317066+00:00",
"inferred_at": "2026-01-09T19:51:08.543341+00:00",
"inferred_by": "enrich_ppids.py"
}
}

138
data/person/ID_XX-XX-XXX_200X_XX-XX-XXX_XXXX_BLAKE-SINGLEY.json → data/person/ID_AU-01-CAN_200X_AU-01-CAN_XXXX_BLAKE-SINGLEY.json
View file

@ -1,11 +1,11 @@
{
"ppid": "ID_XX-XX-XXX_200X_XX-XX-XXX_XXXX_BLAKE-SINGLEY",
"ppid": "ID_AU-01-CAN_200X_AU-01-CAN_XXXX_BLAKE-SINGLEY",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-01-CAN",
"first_date": "200X",
"last_location": "XX-XX-XXX",
"last_location": "AU-01-CAN",
"last_date": "XXXX",
"name_tokens": [
"BLAKE",
@ -14,7 +14,9 @@
"first_date_source": "inferred_birth_decade.primary_value",
"first_date_alternatives": [
"199X"
]
],
"first_location_source": "inferred_birth_settlement",
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "Blake Singley",
@ -84,7 +86,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/blake-singley-0765a2219_20251214T103810Z.json"
],
"modified_at": "2026-01-09T19:18:13.157253+00:00",
"modified_at": "2026-01-09T19:50:52.991131+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "blake-singley-0765a2219",
@ -97,6 +99,17 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_200X_XX-XX-XXX_XXXX_BLAKE-SINGLEY",
"new_ppid": "ID_AU-01-CAN_200X_AU-01-CAN_XXXX_BLAKE-SINGLEY",
"changed_at": "2026-01-09T19:50:52.991128+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -111,7 +124,7 @@
"primary_rationale": "2001 is in 200X, but range extends into 199X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_experience_heuristic",
"inference_chain": [
{
"step": 1,
@ -160,7 +173,118 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 2001 spans decades 199X/200X",
"inferred_at": "2026-01-09T19:18:13.157237+00:00",
"inferred_at": "2026-01-09T19:50:52.974725+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_birth_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_job_location",
"inference_chain": [
{
"step": 1,
"observation": "Earliest job with location found (no education location available)",
"source_field": "profile_data.experience",
"source_value": {
"company": "National Library of Australia",
"title": "Director Rights Management",
"date_range": "Feb 2024 - Present • 2 months",
"location": "Canberra, Australian Capital Territory, Australia"
}
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australian Capital Territory, Australia",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"First job location represents early life region"
],
"assumption_note": "Job location is weak proxy for birth location; person likely relocated for work",
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:50:52.981782+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_current_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "medium",
"inference_provenance": {
"method": "profile_location",
"inference_chain": [
{
"step": 1,
"observation": "Profile location field found",
"source_field": "profile_data.location",
"source_value": "Canberra, Australian Capital Territory, Australia (AU)"
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australian Capital Territory, Australia (AU)",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"Profile location is up-to-date",
"Profile location represents current residence"
],
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:50:52.991110+00:00",
"inferred_by": "enrich_ppids.py"
}
}

150
data/person/ID_XX-XX-XXX_200X_XX-XX-XXX_XXXX_LILIA-WALSH.json → data/person/ID_AU-01-CAN_200X_AU-01-CAN_XXXX_LILIA-WALSH.json
View file

@ -1,11 +1,11 @@
{
"ppid": "ID_XX-XX-XXX_200X_XX-XX-XXX_XXXX_LILIA-WALSH",
"ppid": "ID_AU-01-CAN_200X_AU-01-CAN_XXXX_LILIA-WALSH",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-01-CAN",
"first_date": "200X",
"last_location": "XX-XX-XXX",
"last_location": "AU-01-CAN",
"last_date": "XXXX",
"name_tokens": [
"LILIA",
@ -14,7 +14,9 @@
"first_date_source": "inferred_birth_decade.primary_value",
"first_date_alternatives": [
"199X"
]
],
"first_location_source": "inferred_birth_settlement",
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "Lilia Walsh",
@ -126,7 +128,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/lilia-walsh-311489220_20251214T103948Z.json"
],
"modified_at": "2026-01-09T19:18:15.269494+00:00",
"modified_at": "2026-01-09T19:51:07.877969+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "lilia-walsh-311489220",
@ -139,6 +141,17 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_200X_XX-XX-XXX_XXXX_LILIA-WALSH",
"new_ppid": "ID_AU-01-CAN_200X_AU-01-CAN_XXXX_LILIA-WALSH",
"changed_at": "2026-01-09T19:51:07.877967+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -153,7 +166,7 @@
"primary_rationale": "2000 is in 200X, but range extends into 199X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_education_heuristic",
"inference_chain": [
{
"step": 1,
@ -202,7 +215,130 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 2000 spans decades 199X/200X",
"inferred_at": "2026-01-09T19:18:15.269436+00:00",
"inferred_at": "2026-01-09T19:51:07.868109+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_birth_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "low",
"inference_provenance": {
"method": "earliest_education_location",
"inference_chain": [
{
"step": 1,
"observation": "Earliest education institution identified",
"source_field": "profile_data.education",
"source_value": {
"institution": "The Australian National University",
"date_range": "2018 - 2021 • 3 years",
"degree": "Flexible Double Degree - Bachelor of Arts/Bachelor of Science, Classical and Ancient Studies, Astrophysics, Science Communication"
}
},
{
"step": 2,
"lookup": "Institution location mapping",
"mapping_source": "DUTCH_UNI_LOCATIONS dictionary",
"mapping_key": "The Australian National University",
"mapping_result": "Canberra, Australia"
},
{
"step": 3,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australia",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 4,
"formatting": "CC-RR-PPP generation",
"components": {
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN"
},
"result": "AU-01-CAN"
}
],
"assumptions": [
"Student attended school near birth/family residence",
"Institution location is representative of early life location"
],
"assumption_note": "University location used as proxy for birth settlement; student may have relocated for education",
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:51:07.873264+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_current_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "medium",
"inference_provenance": {
"method": "profile_location",
"inference_chain": [
{
"step": 1,
"observation": "Profile location field found",
"source_field": "profile_data.location",
"source_value": "Canberra, Australian Capital Territory, Australia (AU)"
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australian Capital Territory, Australia (AU)",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"Profile location is up-to-date",
"Profile location represents current residence"
],
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:51:07.877959+00:00",
"inferred_by": "enrich_ppids.py"
}
}

138
data/person/ID_XX-XX-XXX_200X_XX-XX-XXX_XXXX_DANIEL-ROSE.json → data/person/ID_AU-01-CAN_200X_AU-02-PAR_XXXX_DANIEL-ROSE.json
View file

@ -1,11 +1,11 @@
{
"ppid": "ID_XX-XX-XXX_200X_XX-XX-XXX_XXXX_DANIEL-ROSE",
"ppid": "ID_AU-01-CAN_200X_AU-02-PAR_XXXX_DANIEL-ROSE",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-01-CAN",
"first_date": "200X",
"last_location": "XX-XX-XXX",
"last_location": "AU-02-PAR",
"last_date": "XXXX",
"name_tokens": [
"DANIEL",
@ -14,7 +14,9 @@
"first_date_source": "inferred_birth_decade.primary_value",
"first_date_alternatives": [
"199X"
]
],
"first_location_source": "inferred_birth_settlement",
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "Daniel Rose",
@ -85,7 +87,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/daniel-rose-89bb5bb0_20251214T104003Z.json"
],
"modified_at": "2026-01-09T19:18:13.722164+00:00",
"modified_at": "2026-01-09T19:50:56.039641+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "daniel-rose-89bb5bb0",
@ -98,6 +100,17 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_200X_XX-XX-XXX_XXXX_DANIEL-ROSE",
"new_ppid": "ID_AU-01-CAN_200X_AU-02-PAR_XXXX_DANIEL-ROSE",
"changed_at": "2026-01-09T19:50:56.039638+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -112,7 +125,7 @@
"primary_rationale": "2000 is in 200X, but range extends into 199X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_experience_heuristic",
"inference_chain": [
{
"step": 1,
@ -161,7 +174,118 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 2000 spans decades 199X/200X",
"inferred_at": "2026-01-09T19:18:13.722153+00:00",
"inferred_at": "2026-01-09T19:50:55.992715+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_birth_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_job_location",
"inference_chain": [
{
"step": 1,
"observation": "Earliest job with location found (no education location available)",
"source_field": "profile_data.experience",
"source_value": {
"company": "Informatech Pty Ltd",
"title": "Senior Network Engineer",
"date_range": "Jan 2023 - Present • 2 years and 10 months",
"location": "Canberra, Australian Capital Territory, Australia"
}
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australian Capital Territory, Australia",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"First job location represents early life region"
],
"assumption_note": "Job location is weak proxy for birth location; person likely relocated for work",
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:50:56.034463+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_current_settlement": {
"value": "Parkes",
"formatted": "AU-02-PAR",
"country_code": "AU",
"region_code": "02",
"settlement_code": "PAR",
"confidence": "medium",
"inference_provenance": {
"method": "profile_location",
"inference_chain": [
{
"step": 1,
"observation": "Profile location field found",
"source_field": "profile_data.location",
"source_value": "Parkes, Australian Capital Territory, Australia (AU)"
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Parkes, Australian Capital Territory, Australia (AU)",
"result": {
"geonames_id": 2153778,
"geonames_name": "Parkes",
"admin1_code": "02",
"admin1_name": "New South Wales",
"feature_code": "PPL",
"latitude": -33.1372,
"longitude": 148.1759
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-02-PAR"
}
],
"assumptions": [
"Profile location is up-to-date",
"Profile location represents current residence"
],
"geonames_data": {
"geonames_id": 2153778,
"geonames_name": "Parkes",
"admin1_code": "02",
"admin1_name": "New South Wales",
"feature_code": "PPL",
"latitude": -33.1372,
"longitude": 148.1759
},
"inferred_at": "2026-01-09T19:50:56.039625+00:00",
"inferred_by": "enrich_ppids.py"
}
}

150
data/person/ID_XX-XX-XXX_198X_XX-XX-XXX_XXXX_JESS-DRAKE.json → data/person/ID_AU-02-BAT_198X_AU-01-CAN_XXXX_JESS-DRAKE.json
View file

@ -1,11 +1,11 @@
{
"ppid": "ID_XX-XX-XXX_198X_XX-XX-XXX_XXXX_JESS-DRAKE",
"ppid": "ID_AU-02-BAT_198X_AU-01-CAN_XXXX_JESS-DRAKE",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-02-BAT",
"first_date": "198X",
"last_location": "XX-XX-XXX",
"last_location": "AU-01-CAN",
"last_date": "XXXX",
"name_tokens": [
"JESS",
@ -14,7 +14,9 @@
"first_date_source": "inferred_birth_decade.primary_value",
"first_date_alternatives": [
"199X"
]
],
"first_location_source": "inferred_birth_settlement",
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "Jess Drake",
@ -182,7 +184,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/jess-drake-618997146_20251214T103858Z.json"
],
"modified_at": "2026-01-09T19:18:17.289685+00:00",
"modified_at": "2026-01-09T19:50:55.192346+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "jess-drake-618997146",
@ -204,6 +206,17 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_198X_XX-XX-XXX_XXXX_JESS-DRAKE",
"new_ppid": "ID_AU-02-BAT_198X_AU-01-CAN_XXXX_JESS-DRAKE",
"changed_at": "2026-01-09T19:50:55.192344+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -218,7 +231,7 @@
"primary_rationale": "1988 is in 198X, but range extends into 199X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_education_heuristic",
"inference_chain": [
{
"step": 1,
@ -267,7 +280,130 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 1988 spans decades 198X/199X",
"inferred_at": "2026-01-09T19:18:17.289618+00:00",
"inferred_at": "2026-01-09T19:50:55.179013+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_birth_settlement": {
"value": "Bathurst",
"formatted": "AU-02-BAT",
"country_code": "AU",
"region_code": "02",
"settlement_code": "BAT",
"confidence": "low",
"inference_provenance": {
"method": "earliest_education_location",
"inference_chain": [
{
"step": 1,
"observation": "Earliest education institution identified",
"source_field": "profile_data.education",
"source_value": {
"institution": "Charles Sturt University",
"date_range": "2010 - 2013 • 3 years",
"degree": "Bachelor's degree, Library and Information Science"
}
},
{
"step": 2,
"lookup": "Institution location mapping",
"mapping_source": "DUTCH_UNI_LOCATIONS dictionary",
"mapping_key": "Charles Sturt University",
"mapping_result": "Bathurst, Australia"
},
{
"step": 3,
"geocoding": "GeoNames resolution",
"query": "Bathurst, Australia",
"result": {
"geonames_id": 2176632,
"geonames_name": "Bathurst",
"admin1_code": "02",
"admin1_name": "New South Wales",
"feature_code": "PPLA2",
"latitude": -33.41665,
"longitude": 149.5806
}
},
{
"step": 4,
"formatting": "CC-RR-PPP generation",
"components": {
"country_code": "AU",
"region_code": "02",
"settlement_code": "BAT"
},
"result": "AU-02-BAT"
}
],
"assumptions": [
"Student attended school near birth/family residence",
"Institution location is representative of early life location"
],
"assumption_note": "University location used as proxy for birth settlement; student may have relocated for education",
"geonames_data": {
"geonames_id": 2176632,
"geonames_name": "Bathurst",
"admin1_code": "02",
"admin1_name": "New South Wales",
"feature_code": "PPLA2",
"latitude": -33.41665,
"longitude": 149.5806
},
"inferred_at": "2026-01-09T19:50:55.186999+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_current_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "medium",
"inference_provenance": {
"method": "profile_location",
"inference_chain": [
{
"step": 1,
"observation": "Profile location field found",
"source_field": "profile_data.location",
"source_value": "Canberra, Australian Capital Territory, Australia (AU)"
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australian Capital Territory, Australia (AU)",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"Profile location is up-to-date",
"Profile location represents current residence"
],
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:50:55.192332+00:00",
"inferred_by": "enrich_ppids.py"
}
}

150
data/person/ID_XX-XX-XXX_198X_XX-XX-XXX_XXXX_NICOLETTE-S.json → data/person/ID_AU-02-BAT_198X_AU-01-CAN_XXXX_NICOLETTE-S.json
View file

@ -1,11 +1,11 @@
{
"ppid": "ID_XX-XX-XXX_198X_XX-XX-XXX_XXXX_NICOLETTE-S",
"ppid": "ID_AU-02-BAT_198X_AU-01-CAN_XXXX_NICOLETTE-S",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-02-BAT",
"first_date": "198X",
"last_location": "XX-XX-XXX",
"last_location": "AU-01-CAN",
"last_date": "XXXX",
"name_tokens": [
"NICOLETTE",
@ -14,7 +14,9 @@
"first_date_source": "inferred_birth_decade.primary_value",
"first_date_alternatives": [
"199X"
]
],
"first_location_source": "inferred_birth_settlement",
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "Nicolette S.",
@ -98,7 +100,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/nicolette-s-6a3b23a0_20251214T103809Z.json"
],
"modified_at": "2026-01-09T19:18:13.064600+00:00",
"modified_at": "2026-01-09T19:51:10.676497+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "nicolette-s-6a3b23a0",
@ -120,6 +122,17 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_198X_XX-XX-XXX_XXXX_NICOLETTE-S",
"new_ppid": "ID_AU-02-BAT_198X_AU-01-CAN_XXXX_NICOLETTE-S",
"changed_at": "2026-01-09T19:51:10.676494+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -134,7 +147,7 @@
"primary_rationale": "1989 is in 198X, but range extends into 199X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_education_heuristic",
"inference_chain": [
{
"step": 1,
@ -183,7 +196,130 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 1989 spans decades 198X/199X",
"inferred_at": "2026-01-09T19:18:13.064554+00:00",
"inferred_at": "2026-01-09T19:51:10.613015+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_birth_settlement": {
"value": "Bathurst",
"formatted": "AU-02-BAT",
"country_code": "AU",
"region_code": "02",
"settlement_code": "BAT",
"confidence": "low",
"inference_provenance": {
"method": "earliest_education_location",
"inference_chain": [
{
"step": 1,
"observation": "Earliest education institution identified",
"source_field": "profile_data.education",
"source_value": {
"institution": "Charles Sturt University",
"date_range": "2013 - 2018 • 5 years",
"degree": "Masters, Information Studies"
}
},
{
"step": 2,
"lookup": "Institution location mapping",
"mapping_source": "DUTCH_UNI_LOCATIONS dictionary",
"mapping_key": "Charles Sturt University",
"mapping_result": "Bathurst, Australia"
},
{
"step": 3,
"geocoding": "GeoNames resolution",
"query": "Bathurst, Australia",
"result": {
"geonames_id": 2176632,
"geonames_name": "Bathurst",
"admin1_code": "02",
"admin1_name": "New South Wales",
"feature_code": "PPLA2",
"latitude": -33.41665,
"longitude": 149.5806
}
},
{
"step": 4,
"formatting": "CC-RR-PPP generation",
"components": {
"country_code": "AU",
"region_code": "02",
"settlement_code": "BAT"
},
"result": "AU-02-BAT"
}
],
"assumptions": [
"Student attended school near birth/family residence",
"Institution location is representative of early life location"
],
"assumption_note": "University location used as proxy for birth settlement; student may have relocated for education",
"geonames_data": {
"geonames_id": 2176632,
"geonames_name": "Bathurst",
"admin1_code": "02",
"admin1_name": "New South Wales",
"feature_code": "PPLA2",
"latitude": -33.41665,
"longitude": 149.5806
},
"inferred_at": "2026-01-09T19:51:10.669561+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_current_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "medium",
"inference_provenance": {
"method": "profile_location",
"inference_chain": [
{
"step": 1,
"observation": "Profile location field found",
"source_field": "profile_data.location",
"source_value": "Canberra, Australian Capital Territory, Australia (AU)"
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australian Capital Territory, Australia (AU)",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"Profile location is up-to-date",
"Profile location represents current residence"
],
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:51:10.676479+00:00",
"inferred_by": "enrich_ppids.py"
}
}

27
data/person/ID_XX-XX-XXX_198X_XX-XX-XXX_XXXX_SUSIE-WATT.json → data/person/ID_AU-02-BAT_198X_AU-01-CAN_XXXX_SUSIE-WATT.json
View file

@ -1,11 +1,11 @@
{
"ppid": "ID_XX-XX-XXX_198X_XX-XX-XXX_XXXX_SUSIE-WATT",
"ppid": "ID_AU-02-BAT_198X_AU-01-CAN_XXXX_SUSIE-WATT",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-02-BAT",
"first_date": "198X",
"last_location": "XX-XX-XXX",
"last_location": "AU-01-CAN",
"last_date": "XXXX",
"name_tokens": [
"SUSIE",
@ -14,7 +14,9 @@
"first_date_source": "inferred_birth_decade.primary_value",
"first_date_alternatives": [
"199X"
]
],
"first_location_source": "inferred_birth_settlement",
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "Susie Watt",
@ -140,7 +142,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/susie-watt-853a62121_20251214T103922Z.json"
],
"modified_at": "2026-01-09T19:18:12.388206+00:00",
"modified_at": "2026-01-09T19:51:15.723711+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "susie-watt-853a62121",
@ -153,6 +155,17 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_198X_XX-XX-XXX_XXXX_SUSIE-WATT",
"new_ppid": "ID_AU-02-BAT_198X_AU-01-CAN_XXXX_SUSIE-WATT",
"changed_at": "2026-01-09T19:47:59.603039+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -167,7 +180,7 @@
"primary_rationale": "1987 is in 198X, but range extends into 199X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_education_heuristic",
"inference_chain": [
{
"step": 1,
@ -216,7 +229,7 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 1987 spans decades 198X/199X",
"inferred_at": "2026-01-09T19:18:12.388139+00:00",
"inferred_at": "2026-01-09T19:51:15.723705+00:00",
"inferred_by": "enrich_ppids.py"
}
}

150
data/person/ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_KASSI-HAYS.json → data/person/ID_AU-02-BAT_199X_AU-01-CAN_XXXX_KASSI-HAYS.json
View file

@ -1,11 +1,11 @@
{
"ppid": "ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_KASSI-HAYS",
"ppid": "ID_AU-02-BAT_199X_AU-01-CAN_XXXX_KASSI-HAYS",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-02-BAT",
"first_date": "199X",
"last_location": "XX-XX-XXX",
"last_location": "AU-01-CAN",
"last_date": "XXXX",
"name_tokens": [
"KASSI",
@ -14,7 +14,9 @@
"first_date_source": "inferred_birth_decade",
"first_date_alternatives": [
"200X"
]
],
"first_location_source": "inferred_birth_settlement",
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "Kassi Hays",
@ -135,7 +137,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/kassi-hays-32545789_20251214T103934Z.json"
],
"modified_at": "2026-01-09T19:18:15.153602+00:00",
"modified_at": "2026-01-09T19:51:06.946928+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "kassi-hays-32545789",
@ -148,6 +150,17 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_KASSI-HAYS",
"new_ppid": "ID_AU-02-BAT_199X_AU-01-CAN_XXXX_KASSI-HAYS",
"changed_at": "2026-01-09T19:51:06.946925+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -156,7 +169,7 @@
"precision": "decade",
"confidence": "low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_education_heuristic",
"inference_chain": [
{
"step": 1,
@ -197,7 +210,130 @@
"Entry age for education/first job: 22 years (±3)",
"Career records are complete in LinkedIn profile"
],
"inferred_at": "2026-01-09T19:18:15.153555+00:00",
"inferred_at": "2026-01-09T19:51:06.927366+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_birth_settlement": {
"value": "Bathurst",
"formatted": "AU-02-BAT",
"country_code": "AU",
"region_code": "02",
"settlement_code": "BAT",
"confidence": "low",
"inference_provenance": {
"method": "earliest_education_location",
"inference_chain": [
{
"step": 1,
"observation": "Earliest education institution identified",
"source_field": "profile_data.education",
"source_value": {
"institution": "Charles Sturt University",
"date_range": "2017 - 2020 • 3 years",
"degree": "Bachelor of Information Studies (Librarianship)"
}
},
{
"step": 2,
"lookup": "Institution location mapping",
"mapping_source": "DUTCH_UNI_LOCATIONS dictionary",
"mapping_key": "Charles Sturt University",
"mapping_result": "Bathurst, Australia"
},
{
"step": 3,
"geocoding": "GeoNames resolution",
"query": "Bathurst, Australia",
"result": {
"geonames_id": 2176632,
"geonames_name": "Bathurst",
"admin1_code": "02",
"admin1_name": "New South Wales",
"feature_code": "PPLA2",
"latitude": -33.41665,
"longitude": 149.5806
}
},
{
"step": 4,
"formatting": "CC-RR-PPP generation",
"components": {
"country_code": "AU",
"region_code": "02",
"settlement_code": "BAT"
},
"result": "AU-02-BAT"
}
],
"assumptions": [
"Student attended school near birth/family residence",
"Institution location is representative of early life location"
],
"assumption_note": "University location used as proxy for birth settlement; student may have relocated for education",
"geonames_data": {
"geonames_id": 2176632,
"geonames_name": "Bathurst",
"admin1_code": "02",
"admin1_name": "New South Wales",
"feature_code": "PPLA2",
"latitude": -33.41665,
"longitude": 149.5806
},
"inferred_at": "2026-01-09T19:51:06.941751+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_current_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "medium",
"inference_provenance": {
"method": "profile_location",
"inference_chain": [
{
"step": 1,
"observation": "Profile location field found",
"source_field": "profile_data.location",
"source_value": "Canberra, Australian Capital Territory, Australia (AU)"
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australian Capital Territory, Australia (AU)",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"Profile location is up-to-date",
"Profile location represents current residence"
],
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:51:06.946912+00:00",
"inferred_by": "enrich_ppids.py"
}
}

150
data/person/ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_LINDA-B.json → data/person/ID_AU-02-BAT_199X_AU-02-PAR_XXXX_LINDA-B.json
View file

@ -1,11 +1,11 @@
{
"ppid": "ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_LINDA-B",
"ppid": "ID_AU-02-BAT_199X_AU-02-PAR_XXXX_LINDA-B",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-02-BAT",
"first_date": "199X",
"last_location": "XX-XX-XXX",
"last_location": "AU-02-PAR",
"last_date": "XXXX",
"name_tokens": [
"LINDA",
@ -14,7 +14,9 @@
"first_date_source": "inferred_birth_decade.primary_value",
"first_date_alternatives": [
"200X"
]
],
"first_location_source": "inferred_birth_settlement",
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "Linda B.",
@ -121,7 +123,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/lindabull_20251214T103834Z.json"
],
"modified_at": "2026-01-09T19:18:13.306953+00:00",
"modified_at": "2026-01-09T19:50:50.816050+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "lindabull",
@ -143,6 +145,17 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_LINDA-B",
"new_ppid": "ID_AU-02-BAT_199X_AU-02-PAR_XXXX_LINDA-B",
"changed_at": "2026-01-09T19:50:50.816047+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -157,7 +170,7 @@
"primary_rationale": "1999 is in 199X, but range extends into 200X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_education_heuristic",
"inference_chain": [
{
"step": 1,
@ -206,7 +219,130 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 1999 spans decades 199X/200X",
"inferred_at": "2026-01-09T19:18:13.306908+00:00",
"inferred_at": "2026-01-09T19:50:50.804943+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_birth_settlement": {
"value": "Bathurst",
"formatted": "AU-02-BAT",
"country_code": "AU",
"region_code": "02",
"settlement_code": "BAT",
"confidence": "low",
"inference_provenance": {
"method": "earliest_education_location",
"inference_chain": [
{
"step": 1,
"observation": "Earliest education institution identified",
"source_field": "profile_data.education",
"source_value": {
"institution": "Charles Sturt University",
"date_range": "2023 - 2024 • 1 year",
"degree": "Master of Library & Information Science - MLIS"
}
},
{
"step": 2,
"lookup": "Institution location mapping",
"mapping_source": "DUTCH_UNI_LOCATIONS dictionary",
"mapping_key": "Charles Sturt University",
"mapping_result": "Bathurst, Australia"
},
{
"step": 3,
"geocoding": "GeoNames resolution",
"query": "Bathurst, Australia",
"result": {
"geonames_id": 2176632,
"geonames_name": "Bathurst",
"admin1_code": "02",
"admin1_name": "New South Wales",
"feature_code": "PPLA2",
"latitude": -33.41665,
"longitude": 149.5806
}
},
{
"step": 4,
"formatting": "CC-RR-PPP generation",
"components": {
"country_code": "AU",
"region_code": "02",
"settlement_code": "BAT"
},
"result": "AU-02-BAT"
}
],
"assumptions": [
"Student attended school near birth/family residence",
"Institution location is representative of early life location"
],
"assumption_note": "University location used as proxy for birth settlement; student may have relocated for education",
"geonames_data": {
"geonames_id": 2176632,
"geonames_name": "Bathurst",
"admin1_code": "02",
"admin1_name": "New South Wales",
"feature_code": "PPLA2",
"latitude": -33.41665,
"longitude": 149.5806
},
"inferred_at": "2026-01-09T19:50:50.810868+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_current_settlement": {
"value": "Parkes",
"formatted": "AU-02-PAR",
"country_code": "AU",
"region_code": "02",
"settlement_code": "PAR",
"confidence": "medium",
"inference_provenance": {
"method": "profile_location",
"inference_chain": [
{
"step": 1,
"observation": "Profile location field found",
"source_field": "profile_data.location",
"source_value": "Parkes, Australian Capital Territory, Australia (AU)"
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Parkes, Australian Capital Territory, Australia (AU)",
"result": {
"geonames_id": 2153778,
"geonames_name": "Parkes",
"admin1_code": "02",
"admin1_name": "New South Wales",
"feature_code": "PPL",
"latitude": -33.1372,
"longitude": 148.1759
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-02-PAR"
}
],
"assumptions": [
"Profile location is up-to-date",
"Profile location represents current residence"
],
"geonames_data": {
"geonames_id": 2153778,
"geonames_name": "Parkes",
"admin1_code": "02",
"admin1_name": "New South Wales",
"feature_code": "PPL",
"latitude": -33.1372,
"longitude": 148.1759
},
"inferred_at": "2026-01-09T19:50:50.816037+00:00",
"inferred_by": "enrich_ppids.py"
}
}

150
data/person/ID_XX-XX-XXX_194X_XX-XX-XXX_XXXX_ANNMARI-JORDENS.json → data/person/ID_AU-02-SYD_194X_AU-01-CAN_XXXX_ANNMARI-JORDENS.json
View file

@ -1,11 +1,11 @@
{
"ppid": "ID_XX-XX-XXX_194X_XX-XX-XXX_XXXX_ANNMARI-JORDENS",
"ppid": "ID_AU-02-SYD_194X_AU-01-CAN_XXXX_ANNMARI-JORDENS",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-02-SYD",
"first_date": "194X",
"last_location": "XX-XX-XXX",
"last_location": "AU-01-CAN",
"last_date": "XXXX",
"name_tokens": [
"ANNMARI",
@ -14,7 +14,9 @@
"first_date_source": "inferred_birth_decade.primary_value",
"first_date_alternatives": [
"193X"
]
],
"first_location_source": "inferred_birth_settlement",
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "Ann-Mari Jordens",
@ -118,7 +120,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/ann-mari-jordens-a8b9aa56_20251214T103855Z.json"
],
"modified_at": "2026-01-09T19:18:14.990652+00:00",
"modified_at": "2026-01-09T19:51:06.501536+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "ann-mari-jordens-a8b9aa56",
@ -131,6 +133,17 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_194X_XX-XX-XXX_XXXX_ANNMARI-JORDENS",
"new_ppid": "ID_AU-02-SYD_194X_AU-01-CAN_XXXX_ANNMARI-JORDENS",
"changed_at": "2026-01-09T19:51:06.501534+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -145,7 +158,7 @@
"primary_rationale": "1940 is in 194X, but range extends into 193X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_education_heuristic",
"inference_chain": [
{
"step": 1,
@ -194,7 +207,130 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 1940 spans decades 193X/194X",
"inferred_at": "2026-01-09T19:18:14.990610+00:00",
"inferred_at": "2026-01-09T19:51:06.460970+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_birth_settlement": {
"value": "Sydney",
"formatted": "AU-02-SYD",
"country_code": "AU",
"region_code": "02",
"settlement_code": "SYD",
"confidence": "low",
"inference_provenance": {
"method": "earliest_education_location",
"inference_chain": [
{
"step": 1,
"observation": "Earliest education institution identified",
"source_field": "profile_data.education",
"source_value": {
"institution": "University of Sydney",
"date_range": "1962 - 1963 • 1 year",
"degree": "Master of Arts (MA), History"
}
},
{
"step": 2,
"lookup": "Institution location mapping",
"mapping_source": "DUTCH_UNI_LOCATIONS dictionary",
"mapping_key": "University of Sydney",
"mapping_result": "Sydney, Australia"
},
{
"step": 3,
"geocoding": "GeoNames resolution",
"query": "Sydney, Australia",
"result": {
"geonames_id": 2147714,
"geonames_name": "Sydney",
"admin1_code": "02",
"admin1_name": "New South Wales",
"feature_code": "PPLA",
"latitude": -33.86785,
"longitude": 151.20732
}
},
{
"step": 4,
"formatting": "CC-RR-PPP generation",
"components": {
"country_code": "AU",
"region_code": "02",
"settlement_code": "SYD"
},
"result": "AU-02-SYD"
}
],
"assumptions": [
"Student attended school near birth/family residence",
"Institution location is representative of early life location"
],
"assumption_note": "University location used as proxy for birth settlement; student may have relocated for education",
"geonames_data": {
"geonames_id": 2147714,
"geonames_name": "Sydney",
"admin1_code": "02",
"admin1_name": "New South Wales",
"feature_code": "PPLA",
"latitude": -33.86785,
"longitude": 151.20732
},
"inferred_at": "2026-01-09T19:51:06.494829+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_current_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "medium",
"inference_provenance": {
"method": "profile_location",
"inference_chain": [
{
"step": 1,
"observation": "Profile location field found",
"source_field": "profile_data.location",
"source_value": "Canberra, Australian Capital Territory, Australia (AU)"
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australian Capital Territory, Australia (AU)",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"Profile location is up-to-date",
"Profile location represents current residence"
],
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:51:06.501515+00:00",
"inferred_by": "enrich_ppids.py"
}
}

150
data/person/ID_XX-XX-XXX_195X_XX-XX-XXX_XXXX_ISOBEL-TRUNDLE.json → data/person/ID_AU-02-SYD_195X_AU-01-CAN_XXXX_ISOBEL-TRUNDLE.json
View file

@ -1,11 +1,11 @@
{
"ppid": "ID_XX-XX-XXX_195X_XX-XX-XXX_XXXX_ISOBEL-TRUNDLE",
"ppid": "ID_AU-02-SYD_195X_AU-01-CAN_XXXX_ISOBEL-TRUNDLE",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-02-SYD",
"first_date": "195X",
"last_location": "XX-XX-XXX",
"last_location": "AU-01-CAN",
"last_date": "XXXX",
"name_tokens": [
"ISOBEL",
@ -14,7 +14,9 @@
"first_date_source": "inferred_birth_decade.primary_value",
"first_date_alternatives": [
"196X"
]
],
"first_location_source": "inferred_birth_settlement",
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "Isobel Trundle",
@ -90,7 +92,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/isobel-trundle-a2565679_20251214T103842Z.json"
],
"modified_at": "2026-01-09T19:18:13.819348+00:00",
"modified_at": "2026-01-09T19:50:56.622176+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "isobel-trundle-a2565679",
@ -103,6 +105,17 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_195X_XX-XX-XXX_XXXX_ISOBEL-TRUNDLE",
"new_ppid": "ID_AU-02-SYD_195X_AU-01-CAN_XXXX_ISOBEL-TRUNDLE",
"changed_at": "2026-01-09T19:50:56.622174+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -117,7 +130,7 @@
"primary_rationale": "1958 is in 195X, but range extends into 196X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_education_heuristic",
"inference_chain": [
{
"step": 1,
@ -166,7 +179,130 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 1958 spans decades 195X/196X",
"inferred_at": "2026-01-09T19:18:13.819319+00:00",
"inferred_at": "2026-01-09T19:50:56.609186+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_birth_settlement": {
"value": "Sydney",
"formatted": "AU-02-SYD",
"country_code": "AU",
"region_code": "02",
"settlement_code": "SYD",
"confidence": "low",
"inference_provenance": {
"method": "earliest_education_location",
"inference_chain": [
{
"step": 1,
"observation": "Earliest education institution identified",
"source_field": "profile_data.education",
"source_value": {
"institution": "UNIVERSITY OF SYDNEY (SYDNEY COLLEGE OF THE ARTS)",
"date_range": "1976 - 1980 • 4 years",
"degree": "Bachelor's Degree, VISUAL COMMUNICATION"
}
},
{
"step": 2,
"lookup": "Institution location mapping",
"mapping_source": "DUTCH_UNI_LOCATIONS dictionary",
"mapping_key": "UNIVERSITY OF SYDNEY (SYDNEY COLLEGE OF THE ARTS)",
"mapping_result": "Sydney, Australia"
},
{
"step": 3,
"geocoding": "GeoNames resolution",
"query": "Sydney, Australia",
"result": {
"geonames_id": 2147714,
"geonames_name": "Sydney",
"admin1_code": "02",
"admin1_name": "New South Wales",
"feature_code": "PPLA",
"latitude": -33.86785,
"longitude": 151.20732
}
},
{
"step": 4,
"formatting": "CC-RR-PPP generation",
"components": {
"country_code": "AU",
"region_code": "02",
"settlement_code": "SYD"
},
"result": "AU-02-SYD"
}
],
"assumptions": [
"Student attended school near birth/family residence",
"Institution location is representative of early life location"
],
"assumption_note": "University location used as proxy for birth settlement; student may have relocated for education",
"geonames_data": {
"geonames_id": 2147714,
"geonames_name": "Sydney",
"admin1_code": "02",
"admin1_name": "New South Wales",
"feature_code": "PPLA",
"latitude": -33.86785,
"longitude": 151.20732
},
"inferred_at": "2026-01-09T19:50:56.616725+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_current_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "medium",
"inference_provenance": {
"method": "profile_location",
"inference_chain": [
{
"step": 1,
"observation": "Profile location field found",
"source_field": "profile_data.location",
"source_value": "Canberra, Australian Capital Territory, Australia (AU)"
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australian Capital Territory, Australia (AU)",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"Profile location is up-to-date",
"Profile location represents current residence"
],
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:50:56.622163+00:00",
"inferred_by": "enrich_ppids.py"
}
}

27
data/person/ID_XX-XX-XXX_196X_XX-XX-XXX_XXXX_CAROLYN-TOW.json → data/person/ID_AU-02-SYD_196X_AU-01-CAN_XXXX_CAROLYN-TOW.json
View file

@ -1,11 +1,11 @@
{
"ppid": "ID_XX-XX-XXX_196X_XX-XX-XXX_XXXX_CAROLYN-TOW",
"ppid": "ID_AU-02-SYD_196X_AU-01-CAN_XXXX_CAROLYN-TOW",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-02-SYD",
"first_date": "196X",
"last_location": "XX-XX-XXX",
"last_location": "AU-01-CAN",
"last_date": "XXXX",
"name_tokens": [
"CAROLYN",
@ -14,7 +14,9 @@
"first_date_source": "inferred_birth_decade.primary_value",
"first_date_alternatives": [
"195X"
]
],
"first_location_source": "inferred_birth_settlement",
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "Carolyn L. S. Tow",
@ -88,7 +90,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/carolyn-l-s-tow-9b483b76_20251214T103827Z.json"
],
"modified_at": "2026-01-09T19:18:11.366304+00:00",
"modified_at": "2026-01-09T19:50:54.607457+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "carolyn-l-s-tow-9b483b76",
@ -101,6 +103,17 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_196X_XX-XX-XXX_XXXX_CAROLYN-TOW",
"new_ppid": "ID_AU-02-SYD_196X_AU-01-CAN_XXXX_CAROLYN-TOW",
"changed_at": "2026-01-09T19:47:58.614204+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -115,7 +128,7 @@
"primary_rationale": "1961 is in 196X, but range extends into 195X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_education_heuristic",
"inference_chain": [
{
"step": 1,
@ -164,7 +177,7 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 1961 spans decades 195X/196X",
"inferred_at": "2026-01-09T19:18:11.366265+00:00",
"inferred_at": "2026-01-09T19:50:54.607450+00:00",
"inferred_by": "enrich_ppids.py"
}
}

150
data/person/ID_XX-XX-XXX_197X_XX-XX-XXX_XXXX_EMMA-JOLLEY.json → data/person/ID_AU-02-SYD_197X_AU-01-CAN_XXXX_EMMA-JOLLEY.json
View file

@ -1,11 +1,11 @@
{
"ppid": "ID_XX-XX-XXX_197X_XX-XX-XXX_XXXX_EMMA-JOLLEY",
"ppid": "ID_AU-02-SYD_197X_AU-01-CAN_XXXX_EMMA-JOLLEY",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-02-SYD",
"first_date": "197X",
"last_location": "XX-XX-XXX",
"last_location": "AU-01-CAN",
"last_date": "XXXX",
"name_tokens": [
"EMMA",
@ -14,7 +14,9 @@
"first_date_source": "inferred_birth_decade.primary_value",
"first_date_alternatives": [
"196X"
]
],
"first_location_source": "inferred_birth_settlement",
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "Emma Jolley",
@ -180,7 +182,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/emma-jolley-2932a174_20251214T103905Z.json"
],
"modified_at": "2026-01-09T19:18:15.080564+00:00",
"modified_at": "2026-01-09T19:51:06.718379+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "emma-jolley-2932a174",
@ -193,6 +195,17 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_197X_XX-XX-XXX_XXXX_EMMA-JOLLEY",
"new_ppid": "ID_AU-02-SYD_197X_AU-01-CAN_XXXX_EMMA-JOLLEY",
"changed_at": "2026-01-09T19:51:06.718377+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -207,7 +220,7 @@
"primary_rationale": "1970 is in 197X, but range extends into 196X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_education_heuristic",
"inference_chain": [
{
"step": 1,
@ -256,7 +269,130 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 1970 spans decades 196X/197X",
"inferred_at": "2026-01-09T19:18:15.080518+00:00",
"inferred_at": "2026-01-09T19:51:06.708466+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_birth_settlement": {
"value": "Sydney",
"formatted": "AU-02-SYD",
"country_code": "AU",
"region_code": "02",
"settlement_code": "SYD",
"confidence": "low",
"inference_provenance": {
"method": "earliest_education_location",
"inference_chain": [
{
"step": 1,
"observation": "Earliest education institution identified",
"source_field": "profile_data.education",
"source_value": {
"institution": "UNSW Australia",
"date_range": "1992 - 1992",
"degree": "Graduate Diploma, Graduate Diploma in Information Management – Archives Administration."
}
},
{
"step": 2,
"lookup": "Institution location mapping",
"mapping_source": "DUTCH_UNI_LOCATIONS dictionary",
"mapping_key": "UNSW Australia",
"mapping_result": "Sydney, Australia"
},
{
"step": 3,
"geocoding": "GeoNames resolution",
"query": "Sydney, Australia",
"result": {
"geonames_id": 2147714,
"geonames_name": "Sydney",
"admin1_code": "02",
"admin1_name": "New South Wales",
"feature_code": "PPLA",
"latitude": -33.86785,
"longitude": 151.20732
}
},
{
"step": 4,
"formatting": "CC-RR-PPP generation",
"components": {
"country_code": "AU",
"region_code": "02",
"settlement_code": "SYD"
},
"result": "AU-02-SYD"
}
],
"assumptions": [
"Student attended school near birth/family residence",
"Institution location is representative of early life location"
],
"assumption_note": "University location used as proxy for birth settlement; student may have relocated for education",
"geonames_data": {
"geonames_id": 2147714,
"geonames_name": "Sydney",
"admin1_code": "02",
"admin1_name": "New South Wales",
"feature_code": "PPLA",
"latitude": -33.86785,
"longitude": 151.20732
},
"inferred_at": "2026-01-09T19:51:06.713382+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_current_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "medium",
"inference_provenance": {
"method": "profile_location",
"inference_chain": [
{
"step": 1,
"observation": "Profile location field found",
"source_field": "profile_data.location",
"source_value": "Canberra, Australian Capital Territory, Australia (AU)"
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australian Capital Territory, Australia (AU)",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"Profile location is up-to-date",
"Profile location represents current residence"
],
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:51:06.718369+00:00",
"inferred_by": "enrich_ppids.py"
}
}

149
data/person/ID_XX-XX-XXX_197X_XX-XX-XXX_XXXX_LIBOR-COUFAL.json → data/person/ID_AU-02-SYD_197X_AU-01-CAN_XXXX_LIBOR-COUFAL.json
View file

@ -1,11 +1,11 @@
{
"ppid": "ID_XX-XX-XXX_197X_XX-XX-XXX_XXXX_LIBOR-COUFAL",
"ppid": "ID_AU-02-SYD_197X_AU-01-CAN_XXXX_LIBOR-COUFAL",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-02-SYD",
"first_date": "197X",
"last_location": "XX-XX-XXX",
"last_location": "AU-01-CAN",
"last_date": "XXXX",
"name_tokens": [
"LIBOR",
@ -14,7 +14,9 @@
"first_date_source": "inferred_birth_decade",
"first_date_alternatives": [
"196X"
]
],
"first_location_source": "inferred_birth_settlement",
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "Libor Coufal",
@ -202,7 +204,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/liborcoufal_20251214T103751Z.json"
],
"modified_at": "2026-01-09T19:18:14.630320+00:00",
"modified_at": "2026-01-09T19:51:03.192230+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "liborcoufal",
@ -215,6 +217,17 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_197X_XX-XX-XXX_XXXX_LIBOR-COUFAL",
"new_ppid": "ID_AU-02-SYD_197X_AU-01-CAN_XXXX_LIBOR-COUFAL",
"changed_at": "2026-01-09T19:51:03.192226+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -223,7 +236,7 @@
"precision": "decade",
"confidence": "low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_education_heuristic",
"inference_chain": [
{
"step": 1,
@ -264,7 +277,129 @@
"Entry age for education/first job: 22 years (±3)",
"Career records are complete in LinkedIn profile"
],
"inferred_at": "2026-01-09T19:18:14.630247+00:00",
"inferred_at": "2026-01-09T19:51:03.098448+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_birth_settlement": {
"value": "Sydney",
"formatted": "AU-02-SYD",
"country_code": "AU",
"region_code": "02",
"settlement_code": "SYD",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_job_location",
"inference_chain": [
{
"step": 1,
"observation": "Earliest job with location found (no education location available)",
"source_field": "profile_data.experience",
"source_value": {
"company": "Silesian University, School of Business Administration",
"title": "Lecturer",
"date_range": "Jan 1997 - Jan 2000 • 3 years",
"location": "District Karvina, Czech Republic"
}
},
{
"step": 2,
"observation": "Earliest job with location found (no education location available)",
"source_field": "profile_data.experience",
"source_value": {
"company": "University of Sydney",
"title": "Library Assistant",
"date_range": "Jan 2001 - Jan 2004 • 3 years",
"location": "Sydney, Australia"
}
},
{
"step": 3,
"geocoding": "GeoNames resolution",
"query": "Sydney, Australia",
"result": {
"geonames_id": 2147714,
"geonames_name": "Sydney",
"admin1_code": "02",
"admin1_name": "New South Wales",
"feature_code": "PPLA",
"latitude": -33.86785,
"longitude": 151.20732
}
},
{
"step": 4,
"formatting": "CC-RR-PPP generation",
"result": "AU-02-SYD"
}
],
"assumptions": [
"First job location represents early life region"
],
"assumption_note": "Job location is weak proxy for birth location; person likely relocated for work",
"geonames_data": {
"geonames_id": 2147714,
"geonames_name": "Sydney",
"admin1_code": "02",
"admin1_name": "New South Wales",
"feature_code": "PPLA",
"latitude": -33.86785,
"longitude": 151.20732
},
"inferred_at": "2026-01-09T19:51:03.179788+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_current_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "medium",
"inference_provenance": {
"method": "profile_location",
"inference_chain": [
{
"step": 1,
"observation": "Profile location field found",
"source_field": "profile_data.location",
"source_value": "Canberra, Australian Capital Territory, Australia (AU)"
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australian Capital Territory, Australia (AU)",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"Profile location is up-to-date",
"Profile location represents current residence"
],
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:51:03.192199+00:00",
"inferred_by": "enrich_ppids.py"
}
}

138
data/person/ID_XX-XX-XXX_197X_XX-XX-XXX_XXXX_TERENCE-INGRAM.json → data/person/ID_AU-02-SYD_197X_AU-07-DEA_XXXX_TERENCE-INGRAM.json
View file

@ -1,11 +1,11 @@
{
"ppid": "ID_XX-XX-XXX_197X_XX-XX-XXX_XXXX_TERENCE-INGRAM",
"ppid": "ID_AU-02-SYD_197X_AU-07-DEA_XXXX_TERENCE-INGRAM",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-02-SYD",
"first_date": "197X",
"last_location": "XX-XX-XXX",
"last_location": "AU-07-DEA",
"last_date": "XXXX",
"name_tokens": [
"TERENCE",
@ -14,7 +14,9 @@
"first_date_source": "inferred_birth_decade.primary_value",
"first_date_alternatives": [
"198X"
]
],
"first_location_source": "inferred_birth_settlement",
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "Terence Ingram",
@ -146,7 +148,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/terence-ingram-1b9a1817_20251214T103848Z.json"
],
"modified_at": "2026-01-09T19:18:13.397952+00:00",
"modified_at": "2026-01-09T19:50:54.027873+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "terence-ingram-1b9a1817",
@ -159,6 +161,17 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_197X_XX-XX-XXX_XXXX_TERENCE-INGRAM",
"new_ppid": "ID_AU-02-SYD_197X_AU-07-DEA_XXXX_TERENCE-INGRAM",
"changed_at": "2026-01-09T19:50:54.027871+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -173,7 +186,7 @@
"primary_rationale": "1979 is in 197X, but range extends into 198X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_education_heuristic",
"inference_chain": [
{
"step": 1,
@ -222,7 +235,118 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 1979 spans decades 197X/198X",
"inferred_at": "2026-01-09T19:18:13.397901+00:00",
"inferred_at": "2026-01-09T19:50:54.017441+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_birth_settlement": {
"value": "Sydney",
"formatted": "AU-02-SYD",
"country_code": "AU",
"region_code": "02",
"settlement_code": "SYD",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_job_location",
"inference_chain": [
{
"step": 1,
"observation": "Earliest job with location found (no education location available)",
"source_field": "profile_data.experience",
"source_value": {
"company": "Social Change Online",
"title": "Senior Java Developer",
"date_range": "Jan 2000 - Nov 2003 • 3 years and 10 months",
"location": "Sydney, Australia"
}
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Sydney, Australia",
"result": {
"geonames_id": 2147714,
"geonames_name": "Sydney",
"admin1_code": "02",
"admin1_name": "New South Wales",
"feature_code": "PPLA",
"latitude": -33.86785,
"longitude": 151.20732
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-02-SYD"
}
],
"assumptions": [
"First job location represents early life region"
],
"assumption_note": "Job location is weak proxy for birth location; person likely relocated for work",
"geonames_data": {
"geonames_id": 2147714,
"geonames_name": "Sydney",
"admin1_code": "02",
"admin1_name": "New South Wales",
"feature_code": "PPLA",
"latitude": -33.86785,
"longitude": 151.20732
},
"inferred_at": "2026-01-09T19:50:54.023017+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_current_settlement": {
"value": "Deakin",
"formatted": "AU-07-DEA",
"country_code": "AU",
"region_code": "07",
"settlement_code": "DEA",
"confidence": "medium",
"inference_provenance": {
"method": "profile_location",
"inference_chain": [
{
"step": 1,
"observation": "Profile location field found",
"source_field": "profile_data.location",
"source_value": "Deakin, Australian Capital Territory, Australia (AU)"
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Deakin, Australian Capital Territory, Australia (AU)",
"result": {
"geonames_id": 2169236,
"geonames_name": "Deakin",
"admin1_code": "07",
"admin1_name": "Victoria",
"feature_code": "PPL",
"latitude": -36.3,
"longitude": 144.96667
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-07-DEA"
}
],
"assumptions": [
"Profile location is up-to-date",
"Profile location represents current residence"
],
"geonames_data": {
"geonames_id": 2169236,
"geonames_name": "Deakin",
"admin1_code": "07",
"admin1_name": "Victoria",
"feature_code": "PPL",
"latitude": -36.3,
"longitude": 144.96667
},
"inferred_at": "2026-01-09T19:50:54.027863+00:00",
"inferred_by": "enrich_ppids.py"
}
}

150
data/person/ID_XX-XX-XXX_198X_XX-XX-XXX_XXXX_KAVAN-MANCHANAYAKE.json → data/person/ID_AU-02-SYD_198X_AU-01-CAN_XXXX_KAVAN-MANCHANAYAKE.json
View file

@ -1,11 +1,11 @@
{
"ppid": "ID_XX-XX-XXX_198X_XX-XX-XXX_XXXX_KAVAN-MANCHANAYAKE",
"ppid": "ID_AU-02-SYD_198X_AU-01-CAN_XXXX_KAVAN-MANCHANAYAKE",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-02-SYD",
"first_date": "198X",
"last_location": "XX-XX-XXX",
"last_location": "AU-01-CAN",
"last_date": "XXXX",
"name_tokens": [
"KAVAN",
@ -14,7 +14,9 @@
"first_date_source": "inferred_birth_decade.primary_value",
"first_date_alternatives": [
"197X"
]
],
"first_location_source": "inferred_birth_settlement",
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "Kavan Manchanayake",
@ -201,7 +203,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/kavanmanchanayake_20251214T103824Z.json"
],
"modified_at": "2026-01-09T19:18:14.292546+00:00",
"modified_at": "2026-01-09T19:51:00.061661+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "kavanmanchanayake",
@ -214,6 +216,17 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_198X_XX-XX-XXX_XXXX_KAVAN-MANCHANAYAKE",
"new_ppid": "ID_AU-02-SYD_198X_AU-01-CAN_XXXX_KAVAN-MANCHANAYAKE",
"changed_at": "2026-01-09T19:51:00.061659+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -228,7 +241,7 @@
"primary_rationale": "1981 is in 198X, but range extends into 197X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_education_heuristic",
"inference_chain": [
{
"step": 1,
@ -277,7 +290,130 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 1981 spans decades 197X/198X",
"inferred_at": "2026-01-09T19:18:14.292442+00:00",
"inferred_at": "2026-01-09T19:51:00.024584+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_birth_settlement": {
"value": "Sydney",
"formatted": "AU-02-SYD",
"country_code": "AU",
"region_code": "02",
"settlement_code": "SYD",
"confidence": "low",
"inference_provenance": {
"method": "earliest_education_location",
"inference_chain": [
{
"step": 1,
"observation": "Earliest education institution identified",
"source_field": "profile_data.education",
"source_value": {
"institution": "University of Sydney",
"date_range": "1999 - 2003 • 4 years",
"degree": "B.E., Bachelor of Software Engineering"
}
},
{
"step": 2,
"lookup": "Institution location mapping",
"mapping_source": "DUTCH_UNI_LOCATIONS dictionary",
"mapping_key": "University of Sydney",
"mapping_result": "Sydney, Australia"
},
{
"step": 3,
"geocoding": "GeoNames resolution",
"query": "Sydney, Australia",
"result": {
"geonames_id": 2147714,
"geonames_name": "Sydney",
"admin1_code": "02",
"admin1_name": "New South Wales",
"feature_code": "PPLA",
"latitude": -33.86785,
"longitude": 151.20732
}
},
{
"step": 4,
"formatting": "CC-RR-PPP generation",
"components": {
"country_code": "AU",
"region_code": "02",
"settlement_code": "SYD"
},
"result": "AU-02-SYD"
}
],
"assumptions": [
"Student attended school near birth/family residence",
"Institution location is representative of early life location"
],
"assumption_note": "University location used as proxy for birth settlement; student may have relocated for education",
"geonames_data": {
"geonames_id": 2147714,
"geonames_name": "Sydney",
"admin1_code": "02",
"admin1_name": "New South Wales",
"feature_code": "PPLA",
"latitude": -33.86785,
"longitude": 151.20732
},
"inferred_at": "2026-01-09T19:51:00.036481+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_current_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "medium",
"inference_provenance": {
"method": "profile_location",
"inference_chain": [
{
"step": 1,
"observation": "Profile location field found",
"source_field": "profile_data.location",
"source_value": "Canberra, Australian Capital Territory, Australia (AU)"
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australian Capital Territory, Australia (AU)",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"Profile location is up-to-date",
"Profile location represents current residence"
],
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:51:00.061639+00:00",
"inferred_by": "enrich_ppids.py"
}
}

150
data/person/ID_XX-XX-XXX_198X_XX-XX-XXX_XXXX_LIHONG-ZHANG.json → data/person/ID_AU-02-SYD_198X_AU-01-CAN_XXXX_LIHONG-ZHANG.json
View file

@ -1,11 +1,11 @@
{
"ppid": "ID_XX-XX-XXX_198X_XX-XX-XXX_XXXX_LIHONG-ZHANG",
"ppid": "ID_AU-02-SYD_198X_AU-01-CAN_XXXX_LIHONG-ZHANG",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-02-SYD",
"first_date": "198X",
"last_location": "XX-XX-XXX",
"last_location": "AU-01-CAN",
"last_date": "XXXX",
"name_tokens": [
"LIHONG",
@ -14,7 +14,9 @@
"first_date_source": "inferred_birth_decade",
"first_date_alternatives": [
"199X"
]
],
"first_location_source": "inferred_birth_settlement",
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "Lihong Zhang",
@ -194,7 +196,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/lihong-zhang-7315227a_20251214T103756Z.json"
],
"modified_at": "2026-01-09T19:18:13.688517+00:00",
"modified_at": "2026-01-09T19:50:55.448747+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "lihong-zhang-7315227a",
@ -207,6 +209,17 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_198X_XX-XX-XXX_XXXX_LIHONG-ZHANG",
"new_ppid": "ID_AU-02-SYD_198X_AU-01-CAN_XXXX_LIHONG-ZHANG",
"changed_at": "2026-01-09T19:50:55.448744+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -215,7 +228,7 @@
"precision": "decade",
"confidence": "low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_education_heuristic",
"inference_chain": [
{
"step": 1,
@ -256,7 +269,130 @@
"Entry age for education/first job: 22 years (±3)",
"Career records are complete in LinkedIn profile"
],
"inferred_at": "2026-01-09T19:18:13.688468+00:00",
"inferred_at": "2026-01-09T19:50:55.432050+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_birth_settlement": {
"value": "Sydney",
"formatted": "AU-02-SYD",
"country_code": "AU",
"region_code": "02",
"settlement_code": "SYD",
"confidence": "low",
"inference_provenance": {
"method": "earliest_education_location",
"inference_chain": [
{
"step": 1,
"observation": "Earliest education institution identified",
"source_field": "profile_data.education",
"source_value": {
"institution": "Macquarie University",
"date_range": "2006 - 2008 • 2 years",
"degree": "Master’s Degree, Education"
}
},
{
"step": 2,
"lookup": "Institution location mapping",
"mapping_source": "DUTCH_UNI_LOCATIONS dictionary",
"mapping_key": "Macquarie University",
"mapping_result": "Sydney, Australia"
},
{
"step": 3,
"geocoding": "GeoNames resolution",
"query": "Sydney, Australia",
"result": {
"geonames_id": 2147714,
"geonames_name": "Sydney",
"admin1_code": "02",
"admin1_name": "New South Wales",
"feature_code": "PPLA",
"latitude": -33.86785,
"longitude": 151.20732
}
},
{
"step": 4,
"formatting": "CC-RR-PPP generation",
"components": {
"country_code": "AU",
"region_code": "02",
"settlement_code": "SYD"
},
"result": "AU-02-SYD"
}
],
"assumptions": [
"Student attended school near birth/family residence",
"Institution location is representative of early life location"
],
"assumption_note": "University location used as proxy for birth settlement; student may have relocated for education",
"geonames_data": {
"geonames_id": 2147714,
"geonames_name": "Sydney",
"admin1_code": "02",
"admin1_name": "New South Wales",
"feature_code": "PPLA",
"latitude": -33.86785,
"longitude": 151.20732
},
"inferred_at": "2026-01-09T19:50:55.440926+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_current_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "medium",
"inference_provenance": {
"method": "profile_location",
"inference_chain": [
{
"step": 1,
"observation": "Profile location field found",
"source_field": "profile_data.location",
"source_value": "Canberra, Australian Capital Territory, Australia (AU)"
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australian Capital Territory, Australia (AU)",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"Profile location is up-to-date",
"Profile location represents current residence"
],
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:50:55.448732+00:00",
"inferred_by": "enrich_ppids.py"
}
}

150
data/person/ID_XX-XX-XXX_198X_XX-XX-XXX_XXXX_CONSTANTINA-YIOMELAKIS.json → data/person/ID_AU-02-SYD_198X_AU-02-PAR_XXXX_CONSTANTINA-YIOMELAKIS.json
View file

@ -1,11 +1,11 @@
{
"ppid": "ID_XX-XX-XXX_198X_XX-XX-XXX_XXXX_CONSTANTINA-YIOMELAKIS",
"ppid": "ID_AU-02-SYD_198X_AU-02-PAR_XXXX_CONSTANTINA-YIOMELAKIS",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-02-SYD",
"first_date": "198X",
"last_location": "XX-XX-XXX",
"last_location": "AU-02-PAR",
"last_date": "XXXX",
"name_tokens": [
"CONSTANTINA",
@ -14,7 +14,9 @@
"first_date_source": "inferred_birth_decade",
"first_date_alternatives": [
"199X"
]
],
"first_location_source": "inferred_birth_settlement",
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "Constantina Yiomelakis",
@ -256,7 +258,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/constantina-yiomelakis-74b601181_20251214T103933Z.json"
],
"modified_at": "2026-01-09T19:18:13.357269+00:00",
"modified_at": "2026-01-09T19:51:05.097092+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "constantina-yiomelakis-74b601181",
@ -278,6 +280,17 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_198X_XX-XX-XXX_XXXX_CONSTANTINA-YIOMELAKIS",
"new_ppid": "ID_AU-02-SYD_198X_AU-02-PAR_XXXX_CONSTANTINA-YIOMELAKIS",
"changed_at": "2026-01-09T19:51:05.097089+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -286,7 +299,7 @@
"precision": "decade",
"confidence": "low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_education_heuristic",
"inference_chain": [
{
"step": 1,
@ -327,7 +340,130 @@
"Entry age for education/first job: 18 years (±3)",
"Career records are complete in LinkedIn profile"
],
"inferred_at": "2026-01-09T19:18:13.357195+00:00",
"inferred_at": "2026-01-09T19:51:04.989754+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_birth_settlement": {
"value": "Sydney",
"formatted": "AU-02-SYD",
"country_code": "AU",
"region_code": "02",
"settlement_code": "SYD",
"confidence": "low",
"inference_provenance": {
"method": "earliest_education_location",
"inference_chain": [
{
"step": 1,
"observation": "Earliest education institution identified",
"source_field": "profile_data.education",
"source_value": {
"institution": "Macquarie University",
"date_range": "2018 - 2021 • 3 years",
"degree": "Bachelor of Archaeology, Specialisation in Egypt & the Near East"
}
},
{
"step": 2,
"lookup": "Institution location mapping",
"mapping_source": "DUTCH_UNI_LOCATIONS dictionary",
"mapping_key": "Macquarie University",
"mapping_result": "Sydney, Australia"
},
{
"step": 3,
"geocoding": "GeoNames resolution",
"query": "Sydney, Australia",
"result": {
"geonames_id": 2147714,
"geonames_name": "Sydney",
"admin1_code": "02",
"admin1_name": "New South Wales",
"feature_code": "PPLA",
"latitude": -33.86785,
"longitude": 151.20732
}
},
{
"step": 4,
"formatting": "CC-RR-PPP generation",
"components": {
"country_code": "AU",
"region_code": "02",
"settlement_code": "SYD"
},
"result": "AU-02-SYD"
}
],
"assumptions": [
"Student attended school near birth/family residence",
"Institution location is representative of early life location"
],
"assumption_note": "University location used as proxy for birth settlement; student may have relocated for education",
"geonames_data": {
"geonames_id": 2147714,
"geonames_name": "Sydney",
"admin1_code": "02",
"admin1_name": "New South Wales",
"feature_code": "PPLA",
"latitude": -33.86785,
"longitude": 151.20732
},
"inferred_at": "2026-01-09T19:51:05.084096+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_current_settlement": {
"value": "Parkes",
"formatted": "AU-02-PAR",
"country_code": "AU",
"region_code": "02",
"settlement_code": "PAR",
"confidence": "medium",
"inference_provenance": {
"method": "profile_location",
"inference_chain": [
{
"step": 1,
"observation": "Profile location field found",
"source_field": "profile_data.location",
"source_value": "Parkes, Australian Capital Territory, Australia (AU)"
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Parkes, Australian Capital Territory, Australia (AU)",
"result": {
"geonames_id": 2153778,
"geonames_name": "Parkes",
"admin1_code": "02",
"admin1_name": "New South Wales",
"feature_code": "PPL",
"latitude": -33.1372,
"longitude": 148.1759
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-02-PAR"
}
],
"assumptions": [
"Profile location is up-to-date",
"Profile location represents current residence"
],
"geonames_data": {
"geonames_id": 2153778,
"geonames_name": "Parkes",
"admin1_code": "02",
"admin1_name": "New South Wales",
"feature_code": "PPL",
"latitude": -33.1372,
"longitude": 148.1759
},
"inferred_at": "2026-01-09T19:51:05.097070+00:00",
"inferred_by": "enrich_ppids.py"
}
}

23
data/person/ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_GAVIN-B.json → data/person/ID_AU-02-SYD_199X_XX-XX-XXX_XXXX_GAVIN-B.json
View file

@ -1,9 +1,9 @@
{
"ppid": "ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_GAVIN-B",
"ppid": "ID_AU-02-SYD_199X_XX-XX-XXX_XXXX_GAVIN-B",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-02-SYD",
"first_date": "199X",
"last_location": "XX-XX-XXX",
"last_date": "XXXX",
@ -14,7 +14,8 @@
"first_date_source": "inferred_birth_decade.primary_value",
"first_date_alternatives": [
"200X"
]
],
"first_location_source": "inferred_birth_settlement"
},
"name": {
"full_name": "Gavin B.",
@ -140,7 +141,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/gavin-b-b72b2596_20251214T103956Z.json"
],
"modified_at": "2026-01-09T19:18:11.547978+00:00",
"modified_at": "2026-01-09T19:51:05.283547+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "gavin-b-b72b2596",
@ -153,6 +154,16 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_GAVIN-B",
"new_ppid": "ID_AU-02-SYD_199X_XX-XX-XXX_XXXX_GAVIN-B",
"changed_at": "2026-01-09T19:47:58.726142+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement"
]
}
],
"inferred_birth_decade": {
@ -167,7 +178,7 @@
"primary_rationale": "1998 is in 199X, but range extends into 200X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_education_heuristic",
"inference_chain": [
{
"step": 1,
@ -216,7 +227,7 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 1998 spans decades 199X/200X",
"inferred_at": "2026-01-09T19:18:11.547875+00:00",
"inferred_at": "2026-01-09T19:51:05.267358+00:00",
"inferred_by": "enrich_ppids.py"
}
}

150
data/person/ID_XX-XX-XXX_200X_XX-XX-XXX_XXXX_JAMES-SCHOFIELD.json → data/person/ID_AU-02-SYD_200X_AU-01-CAN_XXXX_JAMES-SCHOFIELD.json
View file

@ -1,11 +1,11 @@
{
"ppid": "ID_XX-XX-XXX_200X_XX-XX-XXX_XXXX_JAMES-SCHOFIELD",
"ppid": "ID_AU-02-SYD_200X_AU-01-CAN_XXXX_JAMES-SCHOFIELD",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-02-SYD",
"first_date": "200X",
"last_location": "XX-XX-XXX",
"last_location": "AU-01-CAN",
"last_date": "XXXX",
"name_tokens": [
"JAMES",
@ -14,7 +14,9 @@
"first_date_source": "inferred_birth_decade",
"first_date_alternatives": [
"200X"
]
],
"first_location_source": "inferred_birth_settlement",
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "James Schofield",
@ -148,7 +150,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/james-schofield-4b6741208_20251214T103755Z.json"
],
"modified_at": "2026-01-09T19:18:14.781411+00:00",
"modified_at": "2026-01-09T19:50:57.432606+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "james-schofield-4b6741208",
@ -170,6 +172,17 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_200X_XX-XX-XXX_XXXX_JAMES-SCHOFIELD",
"new_ppid": "ID_AU-02-SYD_200X_AU-01-CAN_XXXX_JAMES-SCHOFIELD",
"changed_at": "2026-01-09T19:50:57.432603+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -178,7 +191,7 @@
"precision": "decade",
"confidence": "low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_education_heuristic",
"inference_chain": [
{
"step": 1,
@ -219,7 +232,130 @@
"Entry age for education/first job: 18 years (±3)",
"Career records are complete in LinkedIn profile"
],
"inferred_at": "2026-01-09T19:18:14.781366+00:00",
"inferred_at": "2026-01-09T19:50:57.421966+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_birth_settlement": {
"value": "Sydney",
"formatted": "AU-02-SYD",
"country_code": "AU",
"region_code": "02",
"settlement_code": "SYD",
"confidence": "low",
"inference_provenance": {
"method": "earliest_education_location",
"inference_chain": [
{
"step": 1,
"observation": "Earliest education institution identified",
"source_field": "profile_data.education",
"source_value": {
"institution": "Macquarie University",
"date_range": "2021 - 2022 • 1 year",
"degree": "Graduate certificate in Ancient History, Ancient History"
}
},
{
"step": 2,
"lookup": "Institution location mapping",
"mapping_source": "DUTCH_UNI_LOCATIONS dictionary",
"mapping_key": "Macquarie University",
"mapping_result": "Sydney, Australia"
},
{
"step": 3,
"geocoding": "GeoNames resolution",
"query": "Sydney, Australia",
"result": {
"geonames_id": 2147714,
"geonames_name": "Sydney",
"admin1_code": "02",
"admin1_name": "New South Wales",
"feature_code": "PPLA",
"latitude": -33.86785,
"longitude": 151.20732
}
},
{
"step": 4,
"formatting": "CC-RR-PPP generation",
"components": {
"country_code": "AU",
"region_code": "02",
"settlement_code": "SYD"
},
"result": "AU-02-SYD"
}
],
"assumptions": [
"Student attended school near birth/family residence",
"Institution location is representative of early life location"
],
"assumption_note": "University location used as proxy for birth settlement; student may have relocated for education",
"geonames_data": {
"geonames_id": 2147714,
"geonames_name": "Sydney",
"admin1_code": "02",
"admin1_name": "New South Wales",
"feature_code": "PPLA",
"latitude": -33.86785,
"longitude": 151.20732
},
"inferred_at": "2026-01-09T19:50:57.427473+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_current_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "medium",
"inference_provenance": {
"method": "profile_location",
"inference_chain": [
{
"step": 1,
"observation": "Profile location field found",
"source_field": "profile_data.location",
"source_value": "Canberra, Australian Capital Territory, Australia (AU)"
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australian Capital Territory, Australia (AU)",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"Profile location is up-to-date",
"Profile location represents current residence"
],
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:50:57.432592+00:00",
"inferred_by": "enrich_ppids.py"
}
}

160
data/person/ID_XX-XX-XXX_197X_XX-XX-XXX_XXXX_JO-RITALE.json → data/person/ID_AU-04-BRI_197X_AU-01-CAN_XXXX_JO-RITALE.json
View file

@ -1,11 +1,11 @@
{
"ppid": "ID_XX-XX-XXX_197X_XX-XX-XXX_XXXX_JO-RITALE",
"ppid": "ID_AU-04-BRI_197X_AU-01-CAN_XXXX_JO-RITALE",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-04-BRI",
"first_date": "197X",
"last_location": "XX-XX-XXX",
"last_location": "AU-01-CAN",
"last_date": "XXXX",
"name_tokens": [
"JO",
@ -14,7 +14,9 @@
"first_date_source": "inferred_birth_decade.primary_value",
"first_date_alternatives": [
"196X"
]
],
"first_location_source": "inferred_birth_settlement",
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "Jo Ritale",
@ -129,7 +131,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/jo-ritale-36622466_20251214T103812Z.json"
],
"modified_at": "2026-01-09T19:18:18.076760+00:00",
"modified_at": "2026-01-09T19:50:55.248577+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "jo-ritale-36622466",
@ -151,6 +153,17 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_197X_XX-XX-XXX_XXXX_JO-RITALE",
"new_ppid": "ID_AU-04-BRI_197X_AU-01-CAN_XXXX_JO-RITALE",
"changed_at": "2026-01-09T19:50:55.248570+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -165,7 +178,7 @@
"primary_rationale": "1971 is in 197X, but range extends into 196X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_education_heuristic",
"inference_chain": [
{
"step": 1,
@ -214,7 +227,140 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 1971 spans decades 196X/197X",
"inferred_at": "2026-01-09T19:18:18.076685+00:00",
"inferred_at": "2026-01-09T19:50:55.223210+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_birth_settlement": {
"value": "Brisbane",
"formatted": "AU-04-BRI",
"country_code": "AU",
"region_code": "04",
"settlement_code": "BRI",
"confidence": "low",
"inference_provenance": {
"method": "earliest_education_location",
"inference_chain": [
{
"step": 1,
"observation": "Earliest education institution identified",
"source_field": "profile_data.education",
"source_value": {
"institution": "The University of Queensland",
"date_range": "1999 - 2000 • 1 year",
"degree": "Bachelor of Arts (Honours), Public/Applied History, First Class"
}
},
{
"step": 2,
"lookup": "Institution location mapping",
"mapping_source": "DUTCH_UNI_LOCATIONS dictionary",
"mapping_key": "The University of Queensland",
"mapping_result": "Brisbane, Australia"
},
{
"step": 3,
"geocoding": "GeoNames resolution",
"query": "Brisbane, Australia",
"result": {
"geonames_id": 2174003,
"geonames_name": "Brisbane",
"admin1_code": "04",
"admin1_name": "Queensland",
"feature_code": "PPLA",
"latitude": -27.46794,
"longitude": 153.02809
}
},
{
"step": 4,
"formatting": "CC-RR-PPP generation",
"components": {
"country_code": "AU",
"region_code": "04",
"settlement_code": "BRI"
},
"result": "AU-04-BRI"
}
],
"assumptions": [
"Student attended school near birth/family residence",
"Institution location is representative of early life location"
],
"assumption_note": "University location used as proxy for birth settlement; student may have relocated for education",
"geonames_data": {
"geonames_id": 2174003,
"geonames_name": "Brisbane",
"admin1_code": "04",
"admin1_name": "Queensland",
"feature_code": "PPLA",
"latitude": -27.46794,
"longitude": 153.02809
},
"inferred_at": "2026-01-09T19:50:55.231078+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_current_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "medium",
"inference_provenance": {
"method": "current_job_location",
"inference_chain": [
{
"step": 1,
"observation": "Profile location field found",
"source_field": "profile_data.location",
"source_value": "Greater Melbourne Area (AU)"
},
{
"step": 2,
"observation": "Current job with location found",
"source_field": "profile_data.experience",
"source_value": {
"company": "National Library of Australia",
"title": "Assistant Director-General, Collection",
"location": "Canberra, Australian Capital Territory, Australia"
}
},
{
"step": 3,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australian Capital Territory, Australia",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 4,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"Current job location represents residence area",
"Person works near where they live"
],
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:50:55.248524+00:00",
"inferred_by": "enrich_ppids.py"
}
}

148
data/person/ID_XX-XX-XXX_197X_XX-XX-XXX_XXXX_MARCUS-HUGHES.json → data/person/ID_AU-04-BRI_197X_AU-01-CAN_XXXX_MARCUS-HUGHES.json
View file

@ -1,11 +1,11 @@
{
"ppid": "ID_XX-XX-XXX_197X_XX-XX-XXX_XXXX_MARCUS-HUGHES",
"ppid": "ID_AU-04-BRI_197X_AU-01-CAN_XXXX_MARCUS-HUGHES",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-04-BRI",
"first_date": "197X",
"last_location": "XX-XX-XXX",
"last_location": "AU-01-CAN",
"last_date": "XXXX",
"name_tokens": [
"MARCUS",
@ -14,7 +14,9 @@
"first_date_source": "inferred_birth_decade.primary_value",
"first_date_alternatives": [
"198X"
]
],
"first_location_source": "inferred_birth_settlement",
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "marcus hughes",
@ -171,7 +173,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/marcus-hughes-0454781b_20251214T104016Z.json"
],
"modified_at": "2026-01-09T19:18:13.569319+00:00",
"modified_at": "2026-01-09T19:50:55.093922+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "marcus-hughes-0454781b",
@ -184,6 +186,17 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_197X_XX-XX-XXX_XXXX_MARCUS-HUGHES",
"new_ppid": "ID_AU-04-BRI_197X_AU-01-CAN_XXXX_MARCUS-HUGHES",
"changed_at": "2026-01-09T19:50:55.093919+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -198,7 +211,7 @@
"primary_rationale": "1975 is in 197X, but range extends into 198X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_experience_heuristic",
"inference_chain": [
{
"step": 1,
@ -247,7 +260,128 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 1975 spans decades 197X/198X",
"inferred_at": "2026-01-09T19:18:13.569277+00:00",
"inferred_at": "2026-01-09T19:50:55.067034+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_birth_settlement": {
"value": "Brisbane",
"formatted": "AU-04-BRI",
"country_code": "AU",
"region_code": "04",
"settlement_code": "BRI",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_job_location",
"inference_chain": [
{
"step": 1,
"observation": "Earliest job with location found (no education location available)",
"source_field": "profile_data.experience",
"source_value": {
"company": "FUSIONS: Australian Network of Clay and Glass Artists",
"title": "Director",
"date_range": "Nov 1998 - Mar 2004 • 5 years and 4 months",
"location": "Brisbane, Australia"
}
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Brisbane, Australia",
"result": {
"geonames_id": 2174003,
"geonames_name": "Brisbane",
"admin1_code": "04",
"admin1_name": "Queensland",
"feature_code": "PPLA",
"latitude": -27.46794,
"longitude": 153.02809
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-04-BRI"
}
],
"assumptions": [
"First job location represents early life region"
],
"assumption_note": "Job location is weak proxy for birth location; person likely relocated for work",
"geonames_data": {
"geonames_id": 2174003,
"geonames_name": "Brisbane",
"admin1_code": "04",
"admin1_name": "Queensland",
"feature_code": "PPLA",
"latitude": -27.46794,
"longitude": 153.02809
},
"inferred_at": "2026-01-09T19:50:55.080197+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_current_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "medium",
"inference_provenance": {
"method": "current_job_location",
"inference_chain": [
{
"step": 1,
"observation": "Profile location field found",
"source_field": "profile_data.location",
"source_value": "Greater Sydney Area (AU)"
},
{
"step": 2,
"observation": "Current job with location found",
"source_field": "profile_data.experience",
"source_value": {
"company": "National Library of Australia",
"title": "Acting Assistan Director - Philanthropy",
"location": "Canberra, Australia"
}
},
{
"step": 3,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australia",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 4,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"Current job location represents residence area",
"Person works near where they live"
],
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:50:55.093905+00:00",
"inferred_by": "enrich_ppids.py"
}
}

150
data/person/ID_XX-XX-XXX_197X_XX-XX-XXX_XXXX_ROWAN-HENDERSON.json → data/person/ID_AU-04-BRI_197X_AU-01-CAN_XXXX_ROWAN-HENDERSON.json
View file

@ -1,11 +1,11 @@
{
"ppid": "ID_XX-XX-XXX_197X_XX-XX-XXX_XXXX_ROWAN-HENDERSON",
"ppid": "ID_AU-04-BRI_197X_AU-01-CAN_XXXX_ROWAN-HENDERSON",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-04-BRI",
"first_date": "197X",
"last_location": "XX-XX-XXX",
"last_location": "AU-01-CAN",
"last_date": "XXXX",
"name_tokens": [
"ROWAN",
@ -14,7 +14,9 @@
"first_date_source": "inferred_birth_decade.primary_value",
"first_date_alternatives": [
"198X"
]
],
"first_location_source": "inferred_birth_settlement",
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "Rowan Henderson",
@ -171,7 +173,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/rowan-henderson-2a65569_20251214T104016Z.json"
],
"modified_at": "2026-01-09T19:18:17.842450+00:00",
"modified_at": "2026-01-09T19:51:28.820845+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "rowan-henderson-2a65569",
@ -184,6 +186,17 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_197X_XX-XX-XXX_XXXX_ROWAN-HENDERSON",
"new_ppid": "ID_AU-04-BRI_197X_AU-01-CAN_XXXX_ROWAN-HENDERSON",
"changed_at": "2026-01-09T19:51:28.820843+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -198,7 +211,7 @@
"primary_rationale": "1979 is in 197X, but range extends into 198X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_education_heuristic",
"inference_chain": [
{
"step": 1,
@ -247,7 +260,130 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 1979 spans decades 197X/198X",
"inferred_at": "2026-01-09T19:18:17.842355+00:00",
"inferred_at": "2026-01-09T19:51:28.793860+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_birth_settlement": {
"value": "Brisbane",
"formatted": "AU-04-BRI",
"country_code": "AU",
"region_code": "04",
"settlement_code": "BRI",
"confidence": "low",
"inference_provenance": {
"method": "earliest_education_location",
"inference_chain": [
{
"step": 1,
"observation": "Earliest education institution identified",
"source_field": "profile_data.education",
"source_value": {
"institution": "The University of Queensland",
"date_range": "1997 - 2003 • 6 years",
"degree": "Bachelor of Arts (Honours)/Laws (Honours), History"
}
},
{
"step": 2,
"lookup": "Institution location mapping",
"mapping_source": "DUTCH_UNI_LOCATIONS dictionary",
"mapping_key": "The University of Queensland",
"mapping_result": "Brisbane, Australia"
},
{
"step": 3,
"geocoding": "GeoNames resolution",
"query": "Brisbane, Australia",
"result": {
"geonames_id": 2174003,
"geonames_name": "Brisbane",
"admin1_code": "04",
"admin1_name": "Queensland",
"feature_code": "PPLA",
"latitude": -27.46794,
"longitude": 153.02809
}
},
{
"step": 4,
"formatting": "CC-RR-PPP generation",
"components": {
"country_code": "AU",
"region_code": "04",
"settlement_code": "BRI"
},
"result": "AU-04-BRI"
}
],
"assumptions": [
"Student attended school near birth/family residence",
"Institution location is representative of early life location"
],
"assumption_note": "University location used as proxy for birth settlement; student may have relocated for education",
"geonames_data": {
"geonames_id": 2174003,
"geonames_name": "Brisbane",
"admin1_code": "04",
"admin1_name": "Queensland",
"feature_code": "PPLA",
"latitude": -27.46794,
"longitude": 153.02809
},
"inferred_at": "2026-01-09T19:51:28.815981+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_current_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "medium",
"inference_provenance": {
"method": "profile_location",
"inference_chain": [
{
"step": 1,
"observation": "Profile location field found",
"source_field": "profile_data.location",
"source_value": "Canberra, Australian Capital Territory, Australia (AU)"
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australian Capital Territory, Australia (AU)",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"Profile location is up-to-date",
"Profile location represents current residence"
],
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:51:28.820835+00:00",
"inferred_by": "enrich_ppids.py"
}
}

148
data/person/ID_XX-XX-XXX_198X_XX-XX-XXX_XXXX_KATE-DISHERQUILL.json → data/person/ID_AU-05-AP_198X_AU-05-AP_XXXX_KATE-DISHERQUILL.json
View file

@ -1,11 +1,11 @@
{
"ppid": "ID_XX-XX-XXX_198X_XX-XX-XXX_XXXX_KATE-DISHERQUILL",
"ppid": "ID_AU-05-AP_198X_AU-05-AP_XXXX_KATE-DISHERQUILL",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-05-AP",
"first_date": "198X",
"last_location": "XX-XX-XXX",
"last_location": "AU-05-AP",
"last_date": "XXXX",
"name_tokens": [
"KATE",
@ -14,7 +14,9 @@
"first_date_source": "inferred_birth_decade",
"first_date_alternatives": [
"199X"
]
],
"first_location_source": "inferred_birth_settlement",
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "Kate Disher-Quill",
@ -120,7 +122,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/kate-disher-quill-29249718a_20251214T103845Z.json"
],
"modified_at": "2026-01-09T19:18:13.776075+00:00",
"modified_at": "2026-01-09T19:50:56.480885+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "kate-disher-quill-29249718a",
@ -133,6 +135,17 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_198X_XX-XX-XXX_XXXX_KATE-DISHERQUILL",
"new_ppid": "ID_AU-05-AP_198X_AU-05-AP_XXXX_KATE-DISHERQUILL",
"changed_at": "2026-01-09T19:50:56.480883+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -141,7 +154,7 @@
"precision": "decade",
"confidence": "low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_education_heuristic",
"inference_chain": [
{
"step": 1,
@ -182,7 +195,128 @@
"Entry age for education/first job: 22 years (±3)",
"Career records are complete in LinkedIn profile"
],
"inferred_at": "2026-01-09T19:18:13.776027+00:00",
"inferred_at": "2026-01-09T19:50:56.465728+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_birth_settlement": {
"value": "Australia Plains",
"formatted": "AU-05-AP",
"country_code": "AU",
"region_code": "05",
"settlement_code": "AP",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_job_location",
"inference_chain": [
{
"step": 1,
"observation": "Earliest job with location found (no education location available)",
"source_field": "profile_data.experience",
"source_value": {
"company": "Kate Disher-Quill (Current)",
"title": "Creative Director Producer Photographer Educator Author",
"date_range": "Jan 2011 - Present • 14 years and 1 month",
"location": "Australia"
}
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Australia",
"result": {
"geonames_id": 2077455,
"geonames_name": "Australia Plains",
"admin1_code": "05",
"admin1_name": "South Australia",
"feature_code": "PPL",
"latitude": -34.09703,
"longitude": 139.15616
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-05-AP"
}
],
"assumptions": [
"First job location represents early life region"
],
"assumption_note": "Job location is weak proxy for birth location; person likely relocated for work",
"geonames_data": {
"geonames_id": 2077455,
"geonames_name": "Australia Plains",
"admin1_code": "05",
"admin1_name": "South Australia",
"feature_code": "PPL",
"latitude": -34.09703,
"longitude": 139.15616
},
"inferred_at": "2026-01-09T19:50:56.470987+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_current_settlement": {
"value": "Australia Plains",
"formatted": "AU-05-AP",
"country_code": "AU",
"region_code": "05",
"settlement_code": "AP",
"confidence": "medium",
"inference_provenance": {
"method": "current_job_location",
"inference_chain": [
{
"step": 1,
"observation": "Profile location field found",
"source_field": "profile_data.location",
"source_value": "Greater Melbourne Area (AU)"
},
{
"step": 2,
"observation": "Current job with location found",
"source_field": "profile_data.experience",
"source_value": {
"company": "Kate Disher-Quill (Current)",
"title": "Creative Director Producer Photographer Educator Author",
"location": "Australia"
}
},
{
"step": 3,
"geocoding": "GeoNames resolution",
"query": "Australia",
"result": {
"geonames_id": 2077455,
"geonames_name": "Australia Plains",
"admin1_code": "05",
"admin1_name": "South Australia",
"feature_code": "PPL",
"latitude": -34.09703,
"longitude": 139.15616
}
},
{
"step": 4,
"formatting": "CC-RR-PPP generation",
"result": "AU-05-AP"
}
],
"assumptions": [
"Current job location represents residence area",
"Person works near where they live"
],
"geonames_data": {
"geonames_id": 2077455,
"geonames_name": "Australia Plains",
"admin1_code": "05",
"admin1_name": "South Australia",
"feature_code": "PPL",
"latitude": -34.09703,
"longitude": 139.15616
},
"inferred_at": "2026-01-09T19:50:56.480870+00:00",
"inferred_by": "enrich_ppids.py"
}
}

138
data/person/ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_CHERIE-CARTER.json → data/person/ID_AU-05-AP_199X_AU-01-CAN_XXXX_CHERIE-CARTER.json
View file

@ -1,11 +1,11 @@
{
"ppid": "ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_CHERIE-CARTER",
"ppid": "ID_AU-05-AP_199X_AU-01-CAN_XXXX_CHERIE-CARTER",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-05-AP",
"first_date": "199X",
"last_location": "XX-XX-XXX",
"last_location": "AU-01-CAN",
"last_date": "XXXX",
"name_tokens": [
"CHERIE",
@ -14,7 +14,9 @@
"first_date_source": "inferred_birth_decade.primary_value",
"first_date_alternatives": [
"200X"
]
],
"first_location_source": "inferred_birth_settlement",
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "Cherie Carter",
@ -99,7 +101,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/cherie-carter-3588421b4_20251214T103913Z.json"
],
"modified_at": "2026-01-09T19:18:16.391398+00:00",
"modified_at": "2026-01-09T19:51:18.440841+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "cherie-carter-3588421b4",
@ -112,6 +114,17 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_CHERIE-CARTER",
"new_ppid": "ID_AU-05-AP_199X_AU-01-CAN_XXXX_CHERIE-CARTER",
"changed_at": "2026-01-09T19:51:18.440839+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -126,7 +139,7 @@
"primary_rationale": "1997 is in 199X, but range extends into 200X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_experience_heuristic",
"inference_chain": [
{
"step": 1,
@ -175,7 +188,118 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 1997 spans decades 199X/200X",
"inferred_at": "2026-01-09T19:18:16.391375+00:00",
"inferred_at": "2026-01-09T19:51:18.428452+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_birth_settlement": {
"value": "Australia Plains",
"formatted": "AU-05-AP",
"country_code": "AU",
"region_code": "05",
"settlement_code": "AP",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_job_location",
"inference_chain": [
{
"step": 1,
"observation": "Earliest job with location found (no education location available)",
"source_field": "profile_data.experience",
"source_value": {
"company": "National Library of Australia",
"title": "Senior Advisor, Curatorial",
"date_range": "Oct 2020 - Present • 5 years and 1 month",
"location": "Australia"
}
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Australia",
"result": {
"geonames_id": 2077455,
"geonames_name": "Australia Plains",
"admin1_code": "05",
"admin1_name": "South Australia",
"feature_code": "PPL",
"latitude": -34.09703,
"longitude": 139.15616
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-05-AP"
}
],
"assumptions": [
"First job location represents early life region"
],
"assumption_note": "Job location is weak proxy for birth location; person likely relocated for work",
"geonames_data": {
"geonames_id": 2077455,
"geonames_name": "Australia Plains",
"admin1_code": "05",
"admin1_name": "South Australia",
"feature_code": "PPL",
"latitude": -34.09703,
"longitude": 139.15616
},
"inferred_at": "2026-01-09T19:51:18.435459+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_current_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "medium",
"inference_provenance": {
"method": "profile_location",
"inference_chain": [
{
"step": 1,
"observation": "Profile location field found",
"source_field": "profile_data.location",
"source_value": "Canberra, Australian Capital Territory, Australia (AU)"
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australian Capital Territory, Australia (AU)",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"Profile location is up-to-date",
"Profile location represents current residence"
],
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:51:18.440828+00:00",
"inferred_by": "enrich_ppids.py"
}
}

149
data/person/ID_XX-XX-XXX_196X_XX-XX-XXX_XXXX_GARRY-STURGESS.json → data/person/ID_AU-07-MEL_196X_AU-01-CAN_XXXX_GARRY-STURGESS.json
View file

@ -1,11 +1,11 @@
{
"ppid": "ID_XX-XX-XXX_196X_XX-XX-XXX_XXXX_GARRY-STURGESS",
"ppid": "ID_AU-07-MEL_196X_AU-01-CAN_XXXX_GARRY-STURGESS",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-07-MEL",
"first_date": "196X",
"last_location": "XX-XX-XXX",
"last_location": "AU-01-CAN",
"last_date": "XXXX",
"name_tokens": [
"GARRY",
@ -14,7 +14,9 @@
"first_date_source": "inferred_birth_decade.primary_value",
"first_date_alternatives": [
"195X"
]
],
"first_location_source": "inferred_birth_settlement",
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "Garry Sturgess",
@ -158,7 +160,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/garry-sturgess-a35a2a22_20251214T103805Z.json"
],
"modified_at": "2026-01-09T19:18:14.651093+00:00",
"modified_at": "2026-01-09T19:51:03.232759+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "garry-sturgess-a35a2a22",
@ -171,6 +173,17 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_196X_XX-XX-XXX_XXXX_GARRY-STURGESS",
"new_ppid": "ID_AU-07-MEL_196X_AU-01-CAN_XXXX_GARRY-STURGESS",
"changed_at": "2026-01-09T19:51:03.232757+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -185,7 +198,7 @@
"primary_rationale": "1961 is in 196X, but range extends into 195X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_experience_heuristic",
"inference_chain": [
{
"step": 1,
@ -234,7 +247,129 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 1961 spans decades 195X/196X",
"inferred_at": "2026-01-09T19:18:14.651065+00:00",
"inferred_at": "2026-01-09T19:51:03.223042+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_birth_settlement": {
"value": "Melbourne",
"formatted": "AU-07-MEL",
"country_code": "AU",
"region_code": "07",
"settlement_code": "MEL",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_job_location",
"inference_chain": [
{
"step": 1,
"observation": "Earliest job with location found (no education location available)",
"source_field": "profile_data.experience",
"source_value": {
"company": "Australian Broadcasting Corporation",
"title": "Presenter The Law Report",
"date_range": "Jan 1984 - Jan 1985 • 1 year",
"location": "Melbourne"
}
},
{
"step": 2,
"observation": "Earliest job with location found (no education location available)",
"source_field": "profile_data.experience",
"source_value": {
"company": "Victorian Bar",
"title": "Barrister",
"date_range": "Jan 1985 - Jan 1989 • 4 years",
"location": "Melbourne, Australia"
}
},
{
"step": 3,
"geocoding": "GeoNames resolution",
"query": "Melbourne, Australia",
"result": {
"geonames_id": 2158177,
"geonames_name": "Melbourne",
"admin1_code": "07",
"admin1_name": "Victoria",
"feature_code": "PPLA",
"latitude": -37.814,
"longitude": 144.96332
}
},
{
"step": 4,
"formatting": "CC-RR-PPP generation",
"result": "AU-07-MEL"
}
],
"assumptions": [
"First job location represents early life region"
],
"assumption_note": "Job location is weak proxy for birth location; person likely relocated for work",
"geonames_data": {
"geonames_id": 2158177,
"geonames_name": "Melbourne",
"admin1_code": "07",
"admin1_name": "Victoria",
"feature_code": "PPLA",
"latitude": -37.814,
"longitude": 144.96332
},
"inferred_at": "2026-01-09T19:51:03.227954+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_current_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "medium",
"inference_provenance": {
"method": "profile_location",
"inference_chain": [
{
"step": 1,
"observation": "Profile location field found",
"source_field": "profile_data.location",
"source_value": "Canberra, Australian Capital Territory, Australia (AU)"
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australian Capital Territory, Australia (AU)",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"Profile location is up-to-date",
"Profile location represents current residence"
],
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:51:03.232750+00:00",
"inferred_by": "enrich_ppids.py"
}
}

150
data/person/ID_XX-XX-XXX_197X_XX-XX-XXX_XXXX_ALICE-GARNER.json → data/person/ID_AU-07-MEL_197X_AU-05-AP_XXXX_ALICE-GARNER.json
View file

@ -1,11 +1,11 @@
{
"ppid": "ID_XX-XX-XXX_197X_XX-XX-XXX_XXXX_ALICE-GARNER",
"ppid": "ID_AU-07-MEL_197X_AU-05-AP_XXXX_ALICE-GARNER",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-07-MEL",
"first_date": "197X",
"last_location": "XX-XX-XXX",
"last_location": "AU-05-AP",
"last_date": "XXXX",
"name_tokens": [
"ALICE",
@ -14,7 +14,9 @@
"first_date_source": "inferred_birth_decade.primary_value",
"first_date_alternatives": [
"196X"
]
],
"first_location_source": "inferred_birth_settlement",
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "Alice Garner",
@ -243,7 +245,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/alice-garner-9167b11b_20251214T103859Z.json"
],
"modified_at": "2026-01-09T19:18:14.726146+00:00",
"modified_at": "2026-01-09T19:51:03.596480+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "alice-garner-9167b11b",
@ -256,6 +258,17 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_197X_XX-XX-XXX_XXXX_ALICE-GARNER",
"new_ppid": "ID_AU-07-MEL_197X_AU-05-AP_XXXX_ALICE-GARNER",
"changed_at": "2026-01-09T19:51:03.596477+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -270,7 +283,7 @@
"primary_rationale": "1971 is in 197X, but range extends into 196X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_education_heuristic",
"inference_chain": [
{
"step": 1,
@ -319,7 +332,130 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 1971 spans decades 196X/197X",
"inferred_at": "2026-01-09T19:18:14.726050+00:00",
"inferred_at": "2026-01-09T19:51:03.577226+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_birth_settlement": {
"value": "Melbourne",
"formatted": "AU-07-MEL",
"country_code": "AU",
"region_code": "07",
"settlement_code": "MEL",
"confidence": "low",
"inference_provenance": {
"method": "earliest_education_location",
"inference_chain": [
{
"step": 1,
"observation": "Earliest education institution identified",
"source_field": "profile_data.education",
"source_value": {
"institution": "University of Melbourne",
"date_range": "1989 - 1993 • 4 years",
"degree": "BA (Hons), History, Fine Arts"
}
},
{
"step": 2,
"lookup": "Institution location mapping",
"mapping_source": "DUTCH_UNI_LOCATIONS dictionary",
"mapping_key": "University of Melbourne",
"mapping_result": "Melbourne, Australia"
},
{
"step": 3,
"geocoding": "GeoNames resolution",
"query": "Melbourne, Australia",
"result": {
"geonames_id": 2158177,
"geonames_name": "Melbourne",
"admin1_code": "07",
"admin1_name": "Victoria",
"feature_code": "PPLA",
"latitude": -37.814,
"longitude": 144.96332
}
},
{
"step": 4,
"formatting": "CC-RR-PPP generation",
"components": {
"country_code": "AU",
"region_code": "07",
"settlement_code": "MEL"
},
"result": "AU-07-MEL"
}
],
"assumptions": [
"Student attended school near birth/family residence",
"Institution location is representative of early life location"
],
"assumption_note": "University location used as proxy for birth settlement; student may have relocated for education",
"geonames_data": {
"geonames_id": 2158177,
"geonames_name": "Melbourne",
"admin1_code": "07",
"admin1_name": "Victoria",
"feature_code": "PPLA",
"latitude": -37.814,
"longitude": 144.96332
},
"inferred_at": "2026-01-09T19:51:03.590775+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_current_settlement": {
"value": "Australia Plains",
"formatted": "AU-05-AP",
"country_code": "AU",
"region_code": "05",
"settlement_code": "AP",
"confidence": "medium",
"inference_provenance": {
"method": "profile_location",
"inference_chain": [
{
"step": 1,
"observation": "Profile location field found",
"source_field": "profile_data.location",
"source_value": "Australia (AU)"
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Australia (AU)",
"result": {
"geonames_id": 2077455,
"geonames_name": "Australia Plains",
"admin1_code": "05",
"admin1_name": "South Australia",
"feature_code": "PPL",
"latitude": -34.09703,
"longitude": 139.15616
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-05-AP"
}
],
"assumptions": [
"Profile location is up-to-date",
"Profile location represents current residence"
],
"geonames_data": {
"geonames_id": 2077455,
"geonames_name": "Australia Plains",
"admin1_code": "05",
"admin1_name": "South Australia",
"feature_code": "PPL",
"latitude": -34.09703,
"longitude": 139.15616
},
"inferred_at": "2026-01-09T19:51:03.596461+00:00",
"inferred_by": "enrich_ppids.py"
}
}

150
data/person/ID_XX-XX-XXX_197X_XX-XX-XXX_XXXX_NIKKI-HENNINGHAM.json → data/person/ID_AU-07-MEL_197X_AU-05-AP_XXXX_NIKKI-HENNINGHAM.json
View file

@ -1,11 +1,11 @@
{
"ppid": "ID_XX-XX-XXX_197X_XX-XX-XXX_XXXX_NIKKI-HENNINGHAM",
"ppid": "ID_AU-07-MEL_197X_AU-05-AP_XXXX_NIKKI-HENNINGHAM",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-07-MEL",
"first_date": "197X",
"last_location": "XX-XX-XXX",
"last_location": "AU-05-AP",
"last_date": "XXXX",
"name_tokens": [
"NIKKI",
@ -14,7 +14,9 @@
"first_date_source": "inferred_birth_decade.primary_value",
"first_date_alternatives": [
"196X"
]
],
"first_location_source": "inferred_birth_settlement",
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "Nikki Henningham",
@ -185,7 +187,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/nikki-henningham-66a1833a_20251214T103806Z.json"
],
"modified_at": "2026-01-09T19:18:16.559914+00:00",
"modified_at": "2026-01-09T19:51:19.047061+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "nikki-henningham-66a1833a",
@ -198,6 +200,17 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_197X_XX-XX-XXX_XXXX_NIKKI-HENNINGHAM",
"new_ppid": "ID_AU-07-MEL_197X_AU-05-AP_XXXX_NIKKI-HENNINGHAM",
"changed_at": "2026-01-09T19:51:19.047058+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -212,7 +225,7 @@
"primary_rationale": "1971 is in 197X, but range extends into 196X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_education_heuristic",
"inference_chain": [
{
"step": 1,
@ -261,7 +274,130 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 1971 spans decades 196X/197X",
"inferred_at": "2026-01-09T19:18:16.559860+00:00",
"inferred_at": "2026-01-09T19:51:19.034181+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_birth_settlement": {
"value": "Melbourne",
"formatted": "AU-07-MEL",
"country_code": "AU",
"region_code": "07",
"settlement_code": "MEL",
"confidence": "low",
"inference_provenance": {
"method": "earliest_education_location",
"inference_chain": [
{
"step": 1,
"observation": "Earliest education institution identified",
"source_field": "profile_data.education",
"source_value": {
"institution": "University of Melbourne",
"date_range": "1995 - 2000 • 5 years",
"degree": "PhD, History"
}
},
{
"step": 2,
"lookup": "Institution location mapping",
"mapping_source": "DUTCH_UNI_LOCATIONS dictionary",
"mapping_key": "University of Melbourne",
"mapping_result": "Melbourne, Australia"
},
{
"step": 3,
"geocoding": "GeoNames resolution",
"query": "Melbourne, Australia",
"result": {
"geonames_id": 2158177,
"geonames_name": "Melbourne",
"admin1_code": "07",
"admin1_name": "Victoria",
"feature_code": "PPLA",
"latitude": -37.814,
"longitude": 144.96332
}
},
{
"step": 4,
"formatting": "CC-RR-PPP generation",
"components": {
"country_code": "AU",
"region_code": "07",
"settlement_code": "MEL"
},
"result": "AU-07-MEL"
}
],
"assumptions": [
"Student attended school near birth/family residence",
"Institution location is representative of early life location"
],
"assumption_note": "University location used as proxy for birth settlement; student may have relocated for education",
"geonames_data": {
"geonames_id": 2158177,
"geonames_name": "Melbourne",
"admin1_code": "07",
"admin1_name": "Victoria",
"feature_code": "PPLA",
"latitude": -37.814,
"longitude": 144.96332
},
"inferred_at": "2026-01-09T19:51:19.040309+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_current_settlement": {
"value": "Australia Plains",
"formatted": "AU-05-AP",
"country_code": "AU",
"region_code": "05",
"settlement_code": "AP",
"confidence": "medium",
"inference_provenance": {
"method": "profile_location",
"inference_chain": [
{
"step": 1,
"observation": "Profile location field found",
"source_field": "profile_data.location",
"source_value": "Australia (AU)"
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Australia (AU)",
"result": {
"geonames_id": 2077455,
"geonames_name": "Australia Plains",
"admin1_code": "05",
"admin1_name": "South Australia",
"feature_code": "PPL",
"latitude": -34.09703,
"longitude": 139.15616
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-05-AP"
}
],
"assumptions": [
"Profile location is up-to-date",
"Profile location represents current residence"
],
"geonames_data": {
"geonames_id": 2077455,
"geonames_name": "Australia Plains",
"admin1_code": "05",
"admin1_name": "South Australia",
"feature_code": "PPL",
"latitude": -34.09703,
"longitude": 139.15616
},
"inferred_at": "2026-01-09T19:51:19.047045+00:00",
"inferred_by": "enrich_ppids.py"
}
}

23
data/person/ID_XX-XX-XXX_197X_XX-XX-XXX_XXXX_MIKE-SHUTTLEWORTH.json → data/person/ID_AU-07-MEL_197X_XX-XX-XXX_XXXX_MIKE-SHUTTLEWORTH.json
View file

@ -1,9 +1,9 @@
{
"ppid": "ID_XX-XX-XXX_197X_XX-XX-XXX_XXXX_MIKE-SHUTTLEWORTH",
"ppid": "ID_AU-07-MEL_197X_XX-XX-XXX_XXXX_MIKE-SHUTTLEWORTH",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-07-MEL",
"first_date": "197X",
"last_location": "XX-XX-XXX",
"last_date": "XXXX",
@ -14,7 +14,8 @@
"first_date_source": "inferred_birth_decade.primary_value",
"first_date_alternatives": [
"198X"
]
],
"first_location_source": "inferred_birth_settlement"
},
"name": {
"full_name": "Mike Shuttleworth",
@ -155,7 +156,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/mshuttleworth_20251214T103828Z.json"
],
"modified_at": "2026-01-09T19:18:11.747888+00:00",
"modified_at": "2026-01-09T19:51:28.898568+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "mshuttleworth",
@ -168,6 +169,16 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_197X_XX-XX-XXX_XXXX_MIKE-SHUTTLEWORTH",
"new_ppid": "ID_AU-07-MEL_197X_XX-XX-XXX_XXXX_MIKE-SHUTTLEWORTH",
"changed_at": "2026-01-09T19:47:58.790724+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement"
]
}
],
"inferred_birth_decade": {
@ -182,7 +193,7 @@
"primary_rationale": "1979 is in 197X, but range extends into 198X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_experience_heuristic",
"inference_chain": [
{
"step": 1,
@ -231,7 +242,7 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 1979 spans decades 197X/198X",
"inferred_at": "2026-01-09T19:18:11.747835+00:00",
"inferred_at": "2026-01-09T19:51:28.892549+00:00",
"inferred_by": "enrich_ppids.py"
}
}

150
data/person/ID_XX-XX-XXX_198X_XX-XX-XXX_XXXX_AMELIA-HARTNEY.json → data/person/ID_AU-07-MEL_198X_AU-01-CAN_XXXX_AMELIA-HARTNEY.json
View file

@ -1,11 +1,11 @@
{
"ppid": "ID_XX-XX-XXX_198X_XX-XX-XXX_XXXX_AMELIA-HARTNEY",
"ppid": "ID_AU-07-MEL_198X_AU-01-CAN_XXXX_AMELIA-HARTNEY",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-07-MEL",
"first_date": "198X",
"last_location": "XX-XX-XXX",
"last_location": "AU-01-CAN",
"last_date": "XXXX",
"name_tokens": [
"AMELIA",
@ -14,7 +14,9 @@
"first_date_source": "inferred_birth_decade.primary_value",
"first_date_alternatives": [
"197X"
]
],
"first_location_source": "inferred_birth_settlement",
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "Amelia Hartney",
@ -165,7 +167,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/amelia-hartney-38b712111_20251214T103940Z.json"
],
"modified_at": "2026-01-09T19:18:15.684189+00:00",
"modified_at": "2026-01-09T19:51:13.436499+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "amelia-hartney-38b712111",
@ -178,6 +180,17 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_198X_XX-XX-XXX_XXXX_AMELIA-HARTNEY",
"new_ppid": "ID_AU-07-MEL_198X_AU-01-CAN_XXXX_AMELIA-HARTNEY",
"changed_at": "2026-01-09T19:51:13.436496+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -192,7 +205,7 @@
"primary_rationale": "1981 is in 198X, but range extends into 197X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_education_heuristic",
"inference_chain": [
{
"step": 1,
@ -241,7 +254,130 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 1981 spans decades 197X/198X",
"inferred_at": "2026-01-09T19:18:15.684132+00:00",
"inferred_at": "2026-01-09T19:51:13.416134+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_birth_settlement": {
"value": "Melbourne",
"formatted": "AU-07-MEL",
"country_code": "AU",
"region_code": "07",
"settlement_code": "MEL",
"confidence": "low",
"inference_provenance": {
"method": "earliest_education_location",
"inference_chain": [
{
"step": 1,
"observation": "Earliest education institution identified",
"source_field": "profile_data.education",
"source_value": {
"institution": "University of Melbourne",
"date_range": "2003 - 2003",
"degree": "Graduate Diploma in Education (Secondary: German, TESOL)"
}
},
{
"step": 2,
"lookup": "Institution location mapping",
"mapping_source": "DUTCH_UNI_LOCATIONS dictionary",
"mapping_key": "University of Melbourne",
"mapping_result": "Melbourne, Australia"
},
{
"step": 3,
"geocoding": "GeoNames resolution",
"query": "Melbourne, Australia",
"result": {
"geonames_id": 2158177,
"geonames_name": "Melbourne",
"admin1_code": "07",
"admin1_name": "Victoria",
"feature_code": "PPLA",
"latitude": -37.814,
"longitude": 144.96332
}
},
{
"step": 4,
"formatting": "CC-RR-PPP generation",
"components": {
"country_code": "AU",
"region_code": "07",
"settlement_code": "MEL"
},
"result": "AU-07-MEL"
}
],
"assumptions": [
"Student attended school near birth/family residence",
"Institution location is representative of early life location"
],
"assumption_note": "University location used as proxy for birth settlement; student may have relocated for education",
"geonames_data": {
"geonames_id": 2158177,
"geonames_name": "Melbourne",
"admin1_code": "07",
"admin1_name": "Victoria",
"feature_code": "PPLA",
"latitude": -37.814,
"longitude": 144.96332
},
"inferred_at": "2026-01-09T19:51:13.429367+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_current_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "medium",
"inference_provenance": {
"method": "profile_location",
"inference_chain": [
{
"step": 1,
"observation": "Profile location field found",
"source_field": "profile_data.location",
"source_value": "Canberra, Australian Capital Territory, Australia (AU)"
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australian Capital Territory, Australia (AU)",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"Profile location is up-to-date",
"Profile location represents current residence"
],
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:51:13.436480+00:00",
"inferred_by": "enrich_ppids.py"
}
}

150
data/person/ID_XX-XX-XXX_198X_XX-XX-XXX_XXXX_BARBARA-LEMON.json → data/person/ID_AU-07-MEL_198X_AU-01-CAN_XXXX_BARBARA-LEMON.json
View file

@ -1,11 +1,11 @@
{
"ppid": "ID_XX-XX-XXX_198X_XX-XX-XXX_XXXX_BARBARA-LEMON",
"ppid": "ID_AU-07-MEL_198X_AU-01-CAN_XXXX_BARBARA-LEMON",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-07-MEL",
"first_date": "198X",
"last_location": "XX-XX-XXX",
"last_location": "AU-01-CAN",
"last_date": "XXXX",
"name_tokens": [
"BARBARA",
@ -14,7 +14,9 @@
"first_date_source": "inferred_birth_decade.primary_value",
"first_date_alternatives": [
"197X"
]
],
"first_location_source": "inferred_birth_settlement",
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "Barbara Lemon",
@ -200,7 +202,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/barbara-lemon-aus_20251214T104003Z.json"
],
"modified_at": "2026-01-09T19:18:16.539137+00:00",
"modified_at": "2026-01-09T19:51:18.597888+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "barbara-lemon-aus",
@ -213,6 +215,17 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_198X_XX-XX-XXX_XXXX_BARBARA-LEMON",
"new_ppid": "ID_AU-07-MEL_198X_AU-01-CAN_XXXX_BARBARA-LEMON",
"changed_at": "2026-01-09T19:51:18.597886+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -227,7 +240,7 @@
"primary_rationale": "1981 is in 198X, but range extends into 197X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_education_heuristic",
"inference_chain": [
{
"step": 1,
@ -276,7 +289,130 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 1981 spans decades 197X/198X",
"inferred_at": "2026-01-09T19:18:16.539061+00:00",
"inferred_at": "2026-01-09T19:51:18.584760+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_birth_settlement": {
"value": "Melbourne",
"formatted": "AU-07-MEL",
"country_code": "AU",
"region_code": "07",
"settlement_code": "MEL",
"confidence": "low",
"inference_provenance": {
"method": "earliest_education_location",
"inference_chain": [
{
"step": 1,
"observation": "Earliest education institution identified",
"source_field": "profile_data.education",
"source_value": {
"institution": "University of Melbourne",
"date_range": "1999 - 2003 • 4 years",
"degree": "Bachelor of Arts (Honours), History and French"
}
},
{
"step": 2,
"lookup": "Institution location mapping",
"mapping_source": "DUTCH_UNI_LOCATIONS dictionary",
"mapping_key": "University of Melbourne",
"mapping_result": "Melbourne, Australia"
},
{
"step": 3,
"geocoding": "GeoNames resolution",
"query": "Melbourne, Australia",
"result": {
"geonames_id": 2158177,
"geonames_name": "Melbourne",
"admin1_code": "07",
"admin1_name": "Victoria",
"feature_code": "PPLA",
"latitude": -37.814,
"longitude": 144.96332
}
},
{
"step": 4,
"formatting": "CC-RR-PPP generation",
"components": {
"country_code": "AU",
"region_code": "07",
"settlement_code": "MEL"
},
"result": "AU-07-MEL"
}
],
"assumptions": [
"Student attended school near birth/family residence",
"Institution location is representative of early life location"
],
"assumption_note": "University location used as proxy for birth settlement; student may have relocated for education",
"geonames_data": {
"geonames_id": 2158177,
"geonames_name": "Melbourne",
"admin1_code": "07",
"admin1_name": "Victoria",
"feature_code": "PPLA",
"latitude": -37.814,
"longitude": 144.96332
},
"inferred_at": "2026-01-09T19:51:18.589722+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_current_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "medium",
"inference_provenance": {
"method": "profile_location",
"inference_chain": [
{
"step": 1,
"observation": "Profile location field found",
"source_field": "profile_data.location",
"source_value": "Canberra, Australian Capital Territory, Australia (AU)"
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australian Capital Territory, Australia (AU)",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"Profile location is up-to-date",
"Profile location represents current residence"
],
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:51:18.597872+00:00",
"inferred_by": "enrich_ppids.py"
}
}

148
data/person/ID_XX-XX-XXX_198X_XX-XX-XXX_XXXX_RUTH-HAZLETON.json → data/person/ID_AU-07-MEL_198X_AU-01-CAN_XXXX_RUTH-HAZLETON.json
View file

@ -1,11 +1,11 @@
{
"ppid": "ID_XX-XX-XXX_198X_XX-XX-XXX_XXXX_RUTH-HAZLETON",
"ppid": "ID_AU-07-MEL_198X_AU-01-CAN_XXXX_RUTH-HAZLETON",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-07-MEL",
"first_date": "198X",
"last_location": "XX-XX-XXX",
"last_location": "AU-01-CAN",
"last_date": "XXXX",
"name_tokens": [
"RUTH",
@ -14,7 +14,9 @@
"first_date_source": "inferred_birth_decade.primary_value",
"first_date_alternatives": [
"197X"
]
],
"first_location_source": "inferred_birth_settlement",
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "Ruth Hazleton",
@ -167,7 +169,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/ruth-hazleton_20251214T103953Z.json"
],
"modified_at": "2026-01-09T19:18:13.649500+00:00",
"modified_at": "2026-01-09T19:51:30.304510+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "ruth-hazleton",
@ -189,6 +191,17 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_198X_XX-XX-XXX_XXXX_RUTH-HAZLETON",
"new_ppid": "ID_AU-07-MEL_198X_AU-01-CAN_XXXX_RUTH-HAZLETON",
"changed_at": "2026-01-09T19:51:30.304507+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -203,7 +216,7 @@
"primary_rationale": "1982 is in 198X, but range extends into 197X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_education_heuristic",
"inference_chain": [
{
"step": 1,
@ -252,7 +265,128 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 1982 spans decades 197X/198X",
"inferred_at": "2026-01-09T19:18:13.649458+00:00",
"inferred_at": "2026-01-09T19:51:30.248464+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_birth_settlement": {
"value": "Melbourne",
"formatted": "AU-07-MEL",
"country_code": "AU",
"region_code": "07",
"settlement_code": "MEL",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_job_location",
"inference_chain": [
{
"step": 1,
"observation": "Earliest job with location found (no education location available)",
"source_field": "profile_data.experience",
"source_value": {
"company": "Self-employed (Current)",
"title": "Professional Musician",
"date_range": "Jan 1995 - Present • 30 years and 9 months",
"location": "Melbourne, Victoria, Australia"
}
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Melbourne, Victoria, Australia",
"result": {
"geonames_id": 2158177,
"geonames_name": "Melbourne",
"admin1_code": "07",
"admin1_name": "Victoria",
"feature_code": "PPLA",
"latitude": -37.814,
"longitude": 144.96332
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-07-MEL"
}
],
"assumptions": [
"First job location represents early life region"
],
"assumption_note": "Job location is weak proxy for birth location; person likely relocated for work",
"geonames_data": {
"geonames_id": 2158177,
"geonames_name": "Melbourne",
"admin1_code": "07",
"admin1_name": "Victoria",
"feature_code": "PPLA",
"latitude": -37.814,
"longitude": 144.96332
},
"inferred_at": "2026-01-09T19:51:30.292722+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_current_settlement": {
"value": "Canberra",
"formatted": "AU-01-CAN",
"country_code": "AU",
"region_code": "01",
"settlement_code": "CAN",
"confidence": "medium",
"inference_provenance": {
"method": "current_job_location",
"inference_chain": [
{
"step": 1,
"observation": "Profile location field found",
"source_field": "profile_data.location",
"source_value": "Greater Melbourne Area (AU)"
},
{
"step": 2,
"observation": "Current job with location found",
"source_field": "profile_data.experience",
"source_value": {
"company": "National Library of Australia",
"title": "Contractor",
"location": "Canberra, Australian Capital Territory, Australia"
}
},
{
"step": 3,
"geocoding": "GeoNames resolution",
"query": "Canberra, Australian Capital Territory, Australia",
"result": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
}
},
{
"step": 4,
"formatting": "CC-RR-PPP generation",
"result": "AU-01-CAN"
}
],
"assumptions": [
"Current job location represents residence area",
"Person works near where they live"
],
"geonames_data": {
"geonames_id": 2172517,
"geonames_name": "Canberra",
"admin1_code": "01",
"admin1_name": "Australian Capital Territory",
"feature_code": "PPLC",
"latitude": -35.28346,
"longitude": 149.12807
},
"inferred_at": "2026-01-09T19:51:30.304494+00:00",
"inferred_by": "enrich_ppids.py"
}
}

81
data/person/ID_XX-XX-XXX_198X_XX-XX-XXX_XXXX_ANNA-KENT.json → data/person/ID_AU-07-MEL_198X_XX-XX-XXX_XXXX_ANNA-KENT.json
View file

@ -1,9 +1,9 @@
{
"ppid": "ID_XX-XX-XXX_198X_XX-XX-XXX_XXXX_ANNA-KENT",
"ppid": "ID_AU-07-MEL_198X_XX-XX-XXX_XXXX_ANNA-KENT",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-07-MEL",
"first_date": "198X",
"last_location": "XX-XX-XXX",
"last_date": "XXXX",
@ -14,7 +14,8 @@
"first_date_source": "inferred_birth_decade.primary_value",
"first_date_alternatives": [
"197X"
]
],
"first_location_source": "inferred_birth_settlement"
},
"name": {
"full_name": "Anna Kent",
@ -181,7 +182,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/anna-kent-99207237_20251214T103925Z.json"
],
"modified_at": "2026-01-09T19:18:15.261141+00:00",
"modified_at": "2026-01-09T19:51:07.658851+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "anna-kent-99207237",
@ -194,6 +195,16 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_198X_XX-XX-XXX_XXXX_ANNA-KENT",
"new_ppid": "ID_AU-07-MEL_198X_XX-XX-XXX_XXXX_ANNA-KENT",
"changed_at": "2026-01-09T19:51:07.658844+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement"
]
}
],
"inferred_birth_decade": {
@ -208,7 +219,7 @@
"primary_rationale": "1982 is in 198X, but range extends into 197X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_experience_heuristic",
"inference_chain": [
{
"step": 1,
@ -257,7 +268,65 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 1982 spans decades 197X/198X",
"inferred_at": "2026-01-09T19:18:15.261104+00:00",
"inferred_at": "2026-01-09T19:51:07.644256+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_birth_settlement": {
"value": "Melbourne",
"formatted": "AU-07-MEL",
"country_code": "AU",
"region_code": "07",
"settlement_code": "MEL",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_job_location",
"inference_chain": [
{
"step": 1,
"observation": "Earliest job with location found (no education location available)",
"source_field": "profile_data.experience",
"source_value": {
"company": "Victoria University",
"title": "Transnational Projects Manager",
"date_range": "Jan 2008 - Apr 2011 • 3 years and 3 months",
"location": "Melbourne, Australia"
}
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Melbourne, Australia",
"result": {
"geonames_id": 2158177,
"geonames_name": "Melbourne",
"admin1_code": "07",
"admin1_name": "Victoria",
"feature_code": "PPLA",
"latitude": -37.814,
"longitude": 144.96332
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "AU-07-MEL"
}
],
"assumptions": [
"First job location represents early life region"
],
"assumption_note": "Job location is weak proxy for birth location; person likely relocated for work",
"geonames_data": {
"geonames_id": 2158177,
"geonames_name": "Melbourne",
"admin1_code": "07",
"admin1_name": "Victoria",
"feature_code": "PPLA",
"latitude": -37.814,
"longitude": 144.96332
},
"inferred_at": "2026-01-09T19:51:07.653825+00:00",
"inferred_by": "enrich_ppids.py"
}
}

93
data/person/ID_XX-XX-XXX_200X_XX-XX-XXX_XXXX_SALWA-CHAIRUNNISA.json → data/person/ID_AU-07-MEL_200X_XX-XX-XXX_XXXX_SALWA-CHAIRUNNISA.json
View file

@ -1,9 +1,9 @@
{
"ppid": "ID_XX-XX-XXX_200X_XX-XX-XXX_XXXX_SALWA-CHAIRUNNISA",
"ppid": "ID_AU-07-MEL_200X_XX-XX-XXX_XXXX_SALWA-CHAIRUNNISA",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "AU-07-MEL",
"first_date": "200X",
"last_location": "XX-XX-XXX",
"last_date": "XXXX",
@ -14,7 +14,8 @@
"first_date_source": "inferred_birth_decade.primary_value",
"first_date_alternatives": [
"199X"
]
],
"first_location_source": "inferred_birth_settlement"
},
"name": {
"full_name": "Salwa Chairunnisa",
@ -124,7 +125,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/salwa-chairunnisa-179886ba_20251214T111937Z.json"
],
"modified_at": "2026-01-09T19:18:15.149297+00:00",
"modified_at": "2026-01-09T19:51:06.923822+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "salwa-chairunnisa-179886ba",
@ -137,6 +138,16 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_200X_XX-XX-XXX_XXXX_SALWA-CHAIRUNNISA",
"new_ppid": "ID_AU-07-MEL_200X_XX-XX-XXX_XXXX_SALWA-CHAIRUNNISA",
"changed_at": "2026-01-09T19:51:06.923807+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement"
]
}
],
"inferred_birth_decade": {
@ -151,7 +162,7 @@
"primary_rationale": "2002 is in 200X, but range extends into 199X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_education_heuristic",
"inference_chain": [
{
"step": 1,
@ -200,7 +211,77 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 2002 spans decades 199X/200X",
"inferred_at": "2026-01-09T19:18:15.149255+00:00",
"inferred_at": "2026-01-09T19:51:06.760795+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_birth_settlement": {
"value": "Melbourne",
"formatted": "AU-07-MEL",
"country_code": "AU",
"region_code": "07",
"settlement_code": "MEL",
"confidence": "low",
"inference_provenance": {
"method": "earliest_education_location",
"inference_chain": [
{
"step": 1,
"observation": "Earliest education institution identified",
"source_field": "profile_data.education",
"source_value": {
"institution": "Monash University",
"date_range": "2024 - 2025 • 1 year",
"degree": "Master of Arts - MA, International Sustainable Tourism Management"
}
},
{
"step": 2,
"lookup": "Institution location mapping",
"mapping_source": "DUTCH_UNI_LOCATIONS dictionary",
"mapping_key": "Monash University",
"mapping_result": "Melbourne, Australia"
},
{
"step": 3,
"geocoding": "GeoNames resolution",
"query": "Melbourne, Australia",
"result": {
"geonames_id": 2158177,
"geonames_name": "Melbourne",
"admin1_code": "07",
"admin1_name": "Victoria",
"feature_code": "PPLA",
"latitude": -37.814,
"longitude": 144.96332
}
},
{
"step": 4,
"formatting": "CC-RR-PPP generation",
"components": {
"country_code": "AU",
"region_code": "07",
"settlement_code": "MEL"
},
"result": "AU-07-MEL"
}
],
"assumptions": [
"Student attended school near birth/family residence",
"Institution location is representative of early life location"
],
"assumption_note": "University location used as proxy for birth settlement; student may have relocated for education",
"geonames_data": {
"geonames_id": 2158177,
"geonames_name": "Melbourne",
"admin1_code": "07",
"admin1_name": "Victoria",
"feature_code": "PPLA",
"latitude": -37.814,
"longitude": 144.96332
},
"inferred_at": "2026-01-09T19:51:06.772890+00:00",
"inferred_by": "enrich_ppids.py"
}
}

6
data/person/ID_BE-BR-BRU_196X_NL-ZH-TH_XXXX_JELLE-BAKKER.json
View file

@ -204,7 +204,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/bakkerjelle_20251214T103236Z.json"
],
"modified_at": "2026-01-09T19:18:18.384392+00:00",
"modified_at": "2026-01-09T19:50:56.729221+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "bakkerjelle",
@ -242,7 +242,7 @@
"primary_rationale": "1968 is in 196X, but range extends into 197X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_education_heuristic",
"inference_chain": [
{
"step": 1,
@ -291,7 +291,7 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 1968 spans decades 196X/197X",
"inferred_at": "2026-01-09T19:18:18.384302+00:00",
"inferred_at": "2026-01-09T19:50:56.729214+00:00",
"inferred_by": "enrich_ppids.py"
}
}

76
data/person/ID_BE-BR-BRU_197X_XX-XX-XXX_XXXX_NEESHA-AMRISH.json → data/person/ID_BE-BR-BRU_197X_IN-25-CHE_XXXX_NEESHA-AMRISH.json
View file

@ -1,11 +1,11 @@
{
"ppid": "ID_BE-BR-BRU_197X_XX-XX-XXX_XXXX_NEESHA-AMRISH",
"ppid": "ID_BE-BR-BRU_197X_IN-25-CHE_XXXX_NEESHA-AMRISH",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "BE-BR-BRU",
"first_date": "197X",
"last_location": "XX-XX-XXX",
"last_location": "IN-25-CHE",
"last_date": "XXXX",
"name_tokens": [
"NEESHA",
@ -15,7 +15,8 @@
"first_location_source": "inferred_birth_settlement",
"first_date_alternatives": [
"198X"
]
],
"last_location_source": "inferred_current_settlement"
},
"name": {
"full_name": "Neesha Amrish",
@ -210,7 +211,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/neesha-amrish-925a15172_20251214T110332Z.json"
],
"modified_at": "2026-01-09T19:18:17.204769+00:00",
"modified_at": "2026-01-09T19:51:25.387741+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "neesha-amrish-925a15172",
@ -224,6 +225,16 @@
"inferred_birth_decade",
"inferred_birth_settlement"
]
},
{
"previous_ppid": "ID_BE-BR-BRU_197X_XX-XX-XXX_XXXX_NEESHA-AMRISH",
"new_ppid": "ID_BE-BR-BRU_197X_IN-25-CHE_XXXX_NEESHA-AMRISH",
"changed_at": "2026-01-09T19:51:25.387728+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_current_settlement"
]
}
],
"inferred_birth_decade": {
@ -232,7 +243,7 @@
"precision": "decade",
"confidence": "low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_education_heuristic",
"inference_chain": [
{
"step": 1,
@ -273,7 +284,60 @@
"Entry age for education/first job: 22 years (±3)",
"Career records are complete in LinkedIn profile"
],
"inferred_at": "2026-01-09T19:18:17.197153+00:00",
"inferred_at": "2026-01-09T19:51:24.480102+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_current_settlement": {
"value": "Chennai",
"formatted": "IN-25-CHE",
"country_code": "IN",
"region_code": "25",
"settlement_code": "CHE",
"confidence": "medium",
"inference_provenance": {
"method": "profile_location",
"inference_chain": [
{
"step": 1,
"observation": "Profile location field found",
"source_field": "profile_data.location",
"source_value": "Chennai, Tamil Nadu, India (IN)"
},
{
"step": 2,
"geocoding": "GeoNames resolution",
"query": "Chennai, Tamil Nadu, India (IN)",
"result": {
"geonames_id": 1264527,
"geonames_name": "Chennai",
"admin1_code": "25",
"admin1_name": "Tamil Nadu",
"feature_code": "PPLA",
"latitude": 13.08784,
"longitude": 80.27847
}
},
{
"step": 3,
"formatting": "CC-RR-PPP generation",
"result": "IN-25-CHE"
}
],
"assumptions": [
"Profile location is up-to-date",
"Profile location represents current residence"
],
"geonames_data": {
"geonames_id": 1264527,
"geonames_name": "Chennai",
"admin1_code": "25",
"admin1_name": "Tamil Nadu",
"feature_code": "PPLA",
"latitude": 13.08784,
"longitude": 80.27847
},
"inferred_at": "2026-01-09T19:51:25.387686+00:00",
"inferred_by": "enrich_ppids.py"
}
}

6
data/person/ID_BE-BR-BRU_197X_NL-NH-AMS_XXXX_PATRICIA-DOCAMPO.json
View file

@ -155,7 +155,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/patricialuquero_20251214T111731Z.json"
],
"modified_at": "2026-01-09T19:18:15.825189+00:00",
"modified_at": "2026-01-09T19:51:14.498913+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "patricialuquero",
@ -184,7 +184,7 @@
"primary_rationale": "1977 is in 197X, but range extends into 198X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_experience_heuristic",
"inference_chain": [
{
"step": 1,
@ -233,7 +233,7 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 1977 spans decades 197X/198X",
"inferred_at": "2026-01-09T19:18:15.825185+00:00",
"inferred_at": "2026-01-09T19:51:14.498907+00:00",
"inferred_by": "enrich_ppids.py"
}
}

6
data/person/ID_BE-BR-BRU_197X_NL-ZH-TH_XXXX_JOSINE-WISKERKE.json
View file

@ -137,7 +137,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/josine-wiskerke-5243901b_20251214T103140Z.json"
],
"modified_at": "2026-01-09T19:18:16.676631+00:00",
"modified_at": "2026-01-09T19:51:21.404971+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "josine-wiskerke-5243901b",
@ -166,7 +166,7 @@
"primary_rationale": "1979 is in 197X, but range extends into 198X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_experience_heuristic",
"inference_chain": [
{
"step": 1,
@ -215,7 +215,7 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 1979 spans decades 197X/198X",
"inferred_at": "2026-01-09T19:18:16.676626+00:00",
"inferred_at": "2026-01-09T19:51:21.404963+00:00",
"inferred_by": "enrich_ppids.py"
}
}

6
data/person/ID_BE-BR-BRU_198X_BE-BR-BRU_XXXX_JEROEN-REYNIERS.json
View file

@ -183,7 +183,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/jeroen-reyniers_20251214T110444Z.json"
],
"modified_at": "2026-01-09T19:18:14.248468+00:00",
"modified_at": "2026-01-09T19:51:04.047382+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "jeroen-reyniers",
@ -221,7 +221,7 @@
"primary_rationale": "1988 is in 198X, but range extends into 199X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_education_heuristic",
"inference_chain": [
{
"step": 1,
@ -270,7 +270,7 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 1988 spans decades 198X/199X",
"inferred_at": "2026-01-09T19:18:14.248456+00:00",
"inferred_at": "2026-01-09T19:51:04.047376+00:00",
"inferred_by": "enrich_ppids.py"
}
}

6
data/person/ID_BE-BR-BRU_198X_NL-NH-AMS_XXXX_MICK-REEHORST.json
View file

@ -183,7 +183,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/mickterreehorst_20251214T110214Z.json"
],
"modified_at": "2026-01-09T19:18:16.613342+00:00",
"modified_at": "2026-01-09T19:51:07.031006+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "mickterreehorst",
@ -221,7 +221,7 @@
"primary_rationale": "1989 is in 198X, but range extends into 199X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_education_heuristic",
"inference_chain": [
{
"step": 1,
@ -270,7 +270,7 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 1989 spans decades 198X/199X",
"inferred_at": "2026-01-09T19:18:16.613336+00:00",
"inferred_at": "2026-01-09T19:51:07.031001+00:00",
"inferred_by": "enrich_ppids.py"
}
}

6
data/person/ID_BE-BR-BRU_198X_XX-XX-XXX_XXXX_BERTINE-BOS.json
View file

@ -176,7 +176,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/bertinebos_20251214T103327Z.json"
],
"modified_at": "2026-01-09T19:18:16.829077+00:00",
"modified_at": "2026-01-09T19:51:22.068826+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "bertinebos",
@ -204,7 +204,7 @@
"primary_rationale": "1981 is in 198X, but range extends into 197X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_education_heuristic",
"inference_chain": [
{
"step": 1,
@ -253,7 +253,7 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 1981 spans decades 197X/198X",
"inferred_at": "2026-01-09T19:18:16.827242+00:00",
"inferred_at": "2026-01-09T19:51:22.066944+00:00",
"inferred_by": "enrich_ppids.py"
}
}

6
data/person/ID_BE-BR-BRU_199X_NL-NH-AMS_XXXX_FARBOD-SAATSAZ.json
View file

@ -231,7 +231,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/farbodbio_20251214T103145Z.json"
],
"modified_at": "2026-01-09T19:18:14.767267+00:00",
"modified_at": "2026-01-09T19:51:04.053128+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "farbodbio",
@ -260,7 +260,7 @@
"primary_rationale": "1992 is in 199X, but range extends into 198X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_education_heuristic",
"inference_chain": [
{
"step": 1,
@ -309,7 +309,7 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 1992 spans decades 198X/199X",
"inferred_at": "2026-01-09T19:18:14.767264+00:00",
"inferred_at": "2026-01-09T19:51:04.053124+00:00",
"inferred_by": "enrich_ppids.py"
}
}

6
data/person/ID_BE-VL-ANT_198X_BE-VL-ANT_XXXX_FREDERIK-VANMEERT.json
View file

@ -139,7 +139,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/frederik-vanmeert-79874763_20251214T111805Z.json"
],
"modified_at": "2026-01-09T19:18:16.382797+00:00",
"modified_at": "2026-01-09T19:50:54.547578+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "frederik-vanmeert-79874763",
@ -171,7 +171,7 @@
"precision": "decade",
"confidence": "low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_education_heuristic",
"inference_chain": [
{
"step": 1,
@ -212,7 +212,7 @@
"Entry age for education/first job: 22 years (±3)",
"Career records are complete in LinkedIn profile"
],
"inferred_at": "2026-01-09T19:18:16.382789+00:00",
"inferred_at": "2026-01-09T19:50:54.547572+00:00",
"inferred_by": "enrich_ppids.py"
}
}

93
data/person/ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_LOUIS-SCHEUNEMAN.json → data/person/ID_BE-VL-ANT_199X_XX-XX-XXX_XXXX_LOUIS-SCHEUNEMAN.json
View file

@ -1,9 +1,9 @@
{
"ppid": "ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_LOUIS-SCHEUNEMAN",
"ppid": "ID_BE-VL-ANT_199X_XX-XX-XXX_XXXX_LOUIS-SCHEUNEMAN",
"ppid_type": "ID",
"ppid_components": {
"type": "ID",
"first_location": "XX-XX-XXX",
"first_location": "BE-VL-ANT",
"first_date": "199X",
"last_location": "XX-XX-XXX",
"last_date": "XXXX",
@ -14,7 +14,8 @@
"first_date_source": "inferred_birth_decade.primary_value",
"first_date_alternatives": [
"198X"
]
],
"first_location_source": "inferred_birth_settlement"
},
"name": {
"full_name": "Louis Scheuneman",
@ -113,7 +114,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/louis-scheuneman-2029318_20251214T112109Z.json"
],
"modified_at": "2026-01-09T19:18:13.376852+00:00",
"modified_at": "2026-01-09T19:51:15.204202+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "louis-scheuneman-2029318",
@ -135,6 +136,16 @@
"inferred_fields": [
"inferred_birth_decade"
]
},
{
"previous_ppid": "ID_XX-XX-XXX_199X_XX-XX-XXX_XXXX_LOUIS-SCHEUNEMAN",
"new_ppid": "ID_BE-VL-ANT_199X_XX-XX-XXX_XXXX_LOUIS-SCHEUNEMAN",
"changed_at": "2026-01-09T19:51:15.204192+00:00",
"reason": "observation_based_inference",
"inferred_fields": [
"inferred_birth_decade",
"inferred_birth_settlement"
]
}
],
"inferred_birth_decade": {
@ -149,7 +160,7 @@
"primary_rationale": "1992 is in 199X, but range extends into 198X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_education_heuristic",
"inference_chain": [
{
"step": 1,
@ -198,7 +209,77 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 1992 spans decades 198X/199X",
"inferred_at": "2026-01-09T19:18:13.373033+00:00",
"inferred_at": "2026-01-09T19:51:15.192665+00:00",
"inferred_by": "enrich_ppids.py"
}
},
"inferred_birth_settlement": {
"value": "Antwerpen",
"formatted": "BE-VL-ANT",
"country_code": "BE",
"region_code": "VL",
"settlement_code": "ANT",
"confidence": "low",
"inference_provenance": {
"method": "earliest_education_location",
"inference_chain": [
{
"step": 1,
"observation": "Earliest education institution identified",
"source_field": "profile_data.education",
"source_value": {
"institution": "Universiteit Antwerpen",
"date_range": "2014 - 2016 • 2 years",
"degree": "Postgraduaat, Informatie- en Bibliotheekwetenschap"
}
},
{
"step": 2,
"lookup": "Institution location mapping",
"mapping_source": "DUTCH_UNI_LOCATIONS dictionary",
"mapping_key": "Universiteit Antwerpen",
"mapping_result": "Antwerpen, Belgium"
},
{
"step": 3,
"geocoding": "GeoNames resolution",
"query": "Antwerpen, Belgium",
"result": {
"geonames_id": 2803138,
"geonames_name": "Antwerpen",
"admin1_code": "VLG",
"admin1_name": "Flanders",
"feature_code": "PPL",
"latitude": 51.22047,
"longitude": 4.40026
}
},
{
"step": 4,
"formatting": "CC-RR-PPP generation",
"components": {
"country_code": "BE",
"region_code": "VL",
"settlement_code": "ANT"
},
"result": "BE-VL-ANT"
}
],
"assumptions": [
"Student attended school near birth/family residence",
"Institution location is representative of early life location"
],
"assumption_note": "University location used as proxy for birth settlement; student may have relocated for education",
"geonames_data": {
"geonames_id": 2803138,
"geonames_name": "Antwerpen",
"admin1_code": "VLG",
"admin1_name": "Flanders",
"feature_code": "PPL",
"latitude": 51.22047,
"longitude": 4.40026
},
"inferred_at": "2026-01-09T19:51:15.201823+00:00",
"inferred_by": "enrich_ppids.py"
}
}

6
data/person/ID_BE-VL-HOV_195X_NL-ZH-TH_XXXX_ALEX-MALLEMS.json
View file

@ -170,7 +170,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/alex-mallems-a5586a16_20251214T112502Z.json"
],
"modified_at": "2026-01-09T19:18:19.020702+00:00",
"modified_at": "2026-01-09T19:51:34.515095+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "alex-mallems-a5586a16",
@ -199,7 +199,7 @@
"primary_rationale": "1959 is in 195X, but range extends into 196X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_experience_heuristic",
"inference_chain": [
{
"step": 1,
@ -248,7 +248,7 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 1959 spans decades 195X/196X",
"inferred_at": "2026-01-09T19:18:19.020693+00:00",
"inferred_at": "2026-01-09T19:51:34.515087+00:00",
"inferred_by": "enrich_ppids.py"
}
}

6
data/person/ID_BE-VL-LEU_198X_NL-NB-EIN_XXXX_JULIEN-MAILFERT.json
View file

@ -222,7 +222,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/julien-mailfert-77292917_20251214T111004Z.json"
],
"modified_at": "2026-01-09T19:18:15.215568+00:00",
"modified_at": "2026-01-09T19:51:13.296883+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "julien-mailfert-77292917",
@ -260,7 +260,7 @@
"primary_rationale": "1987 is in 198X, but range extends into 199X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_education_heuristic",
"inference_chain": [
{
"step": 1,
@ -309,7 +309,7 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 1987 spans decades 198X/199X",
"inferred_at": "2026-01-09T19:18:15.215562+00:00",
"inferred_at": "2026-01-09T19:51:13.296879+00:00",
"inferred_by": "enrich_ppids.py"
}
}

6
data/person/ID_BE-VL-LEU_198X_NL-NB-EIN_XXXX_S-AFZAL.json
View file

@ -251,7 +251,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/rehanafzal_20251214T110816Z.json"
],
"modified_at": "2026-01-09T19:18:17.449297+00:00",
"modified_at": "2026-01-09T19:51:28.147706+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "rehanafzal",
@ -280,7 +280,7 @@
"primary_rationale": "1980 is in 198X, but range extends into 197X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_education_heuristic",
"inference_chain": [
{
"step": 1,
@ -329,7 +329,7 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 1980 spans decades 197X/198X",
"inferred_at": "2026-01-09T19:18:17.449291+00:00",
"inferred_at": "2026-01-09T19:51:28.147700+00:00",
"inferred_by": "enrich_ppids.py"
}
}

6
data/person/ID_BE-VL-MEC_199X_NL-NH-AMS_XXXX_EMMA-BENTHEM.json
View file

@ -184,7 +184,7 @@
"source_files": [
"/Users/kempersc/apps/glam/data/custodian/person/entity/emma-van-benthem-a603901a1_20251214T110115Z.json"
],
"modified_at": "2026-01-09T19:18:14.036979+00:00",
"modified_at": "2026-01-09T19:50:58.533169+00:00",
"modified_by": "enrich_ppids.py"
},
"linkedin_slug": "emma-van-benthem-a603901a1",
@ -213,7 +213,7 @@
"primary_rationale": "1999 is in 199X, but range extends into 200X",
"confidence": "very_low",
"inference_provenance": {
"method": "earliest_observation_heuristic",
"method": "earliest_education_heuristic",
"inference_chain": [
{
"step": 1,
@ -262,7 +262,7 @@
"Career records are complete in LinkedIn profile"
],
"boundary_note": "Birth year estimate 1999 spans decades 199X/200X",
"inferred_at": "2026-01-09T19:18:14.036973+00:00",
"inferred_at": "2026-01-09T19:50:58.533158+00:00",
"inferred_by": "enrich_ppids.py"
}
}

Some files were not shown because too many files have changed in this diff Show more