1e01639c56
Rename 144 custodian files from XXX placeholders to resolved city codes:
- BR (65): ASA, RBR, MAN, FAZ, MAC, VIT, FOR, GUA, BRE, GOI, SLU, BHO, XAN, CGR, CUI, etc.
- CH (24): ZUR, BER, GEN, BAL, LUC, etc.
- MX (23): MEX, GDL, MTY, PUE, etc.
- CL (9): SCL, VAL, etc.
- CZ (5): PRG, BRN, MSV, etc.
- KR (4): SEL, etc.
- GB (4): LON, etc.
- FR (3): PAR, etc.
- IN (2): DEL, etc.
- PH, JP, EE (1 each)
City codes derived from GeoNames reverse geocoding using institution coordinates.
GHCID format: {COUNTRY}-{REGION}-{CITY}-{TYPE}-{ABBREV}
156 lines
5.7 KiB
YAML
156 lines
5.7 KiB
YAML
original_entry:
|
|
name: USP/UNICAMP/UNESP
|
|
institution_type: EDUCATION_PROVIDER
|
|
source: CH-Annotator (latin_american_institutions_AUTHORITATIVE_ch_annotator.yaml)
|
|
identifiers:
|
|
- identifier_scheme: GHCID
|
|
identifier_value: BR-SP-XXX-E-U
|
|
- identifier_scheme: GHCID_NUMERIC
|
|
identifier_value: '2268910688007071813'
|
|
- &id001
|
|
identifier_scheme: OLD_ID
|
|
identifier_value: https://w3id.org/heritage/custodian/br/usp-unicamp-unesp
|
|
- identifier_scheme: GHCID_UUID
|
|
identifier_value: 9aca17ca-26ee-55a5-b0a0-097c4fa12dbf
|
|
identifier_url: urn:uuid:9aca17ca-26ee-55a5-b0a0-097c4fa12dbf
|
|
- identifier_scheme: GHCID_UUID_SHA256
|
|
identifier_value: 1f7cca3f-e1bf-8845-9ffd-e0c495e43ab4
|
|
identifier_url: urn:uuid:1f7cca3f-e1bf-8845-9ffd-e0c495e43ab4
|
|
- identifier_scheme: RECORD_ID
|
|
identifier_value: 019a58fd-3227-7644-9eff-6acf958d2228
|
|
identifier_url: urn:uuid:019a58fd-3227-7644-9eff-6acf958d2228
|
|
- &id002
|
|
identifier_scheme: OLD_ID
|
|
identifier_value: 2268910688007071813
|
|
locations:
|
|
- country: BR
|
|
region: SÃO PAULO
|
|
processing_timestamp: '2025-12-06T23:35:51.996651+00:00'
|
|
ghcid:
|
|
ghcid_current: BR-SP-LSD-E-UUU
|
|
ghcid_original: BR-SA-XXX-E-UUU
|
|
ghcid_uuid: 05f54b3d-36fc-5d22-a346-03e46670759e
|
|
ghcid_uuid_sha256: 831323db-d387-8058-23b4-a897313a83fa
|
|
ghcid_numeric: 9444932270579765336
|
|
record_id: 1b7dccfb-762c-4d3b-954a-aa0ba9a38752
|
|
generation_timestamp: '2025-12-06T23:35:51.996651+00:00'
|
|
location_resolution:
|
|
method: GOOGLE_PLACES_GEONAMES
|
|
country_code: BR
|
|
region_code: SP
|
|
region_name: São Paulo
|
|
city_code: LSD
|
|
city_name: Loteamento Solar de Campinas
|
|
geonames_id: 13005473
|
|
feature_code: PPL
|
|
google_place_id: ChIJtU3SBbDGyJQRltcEzw5128Y
|
|
latitude: -22.818439299999998
|
|
longitude: -47.0647206
|
|
resolution_date: '2025-12-07T16:39:12.242790+00:00'
|
|
ghcid_history:
|
|
- ghcid: BR-SA-XXX-E-UUU
|
|
ghcid_numeric: 9444932270579765336
|
|
valid_from: '2025-12-06T23:35:51.996651+00:00'
|
|
reason: Initial GHCID from CH-Annotator (latin_american_institutions_AUTHORITATIVE_ch_annotator.yaml)
|
|
valid_to: '2025-12-07T16:39:12.242790+00:00'
|
|
- ghcid: BR-SP-LSD-E-UUU
|
|
ghcid_numeric: 9444932270579765336
|
|
valid_from: '2025-12-07T16:39:12.242790+00:00'
|
|
reason: 'Location resolved via Google Places + GeoNames: Loteamento Solar de Campinas
|
|
(SP)'
|
|
custodian_name:
|
|
claim_type: custodian_name
|
|
claim_value: USP/UNICAMP/UNESP
|
|
source_type: ch_annotator
|
|
identifiers:
|
|
- identifier_scheme: GHCID
|
|
identifier_value: BR-SP-LSD-E-UUU
|
|
- identifier_scheme: GHCID_UUID
|
|
identifier_value: 05f54b3d-36fc-5d22-a346-03e46670759e
|
|
- identifier_scheme: GHCID_UUID_SHA256
|
|
identifier_value: 831323db-d387-8058-23b4-a897313a83fa
|
|
- identifier_scheme: GHCID_NUMERIC
|
|
identifier_value: '9444932270579765336'
|
|
- identifier_scheme: RECORD_ID
|
|
identifier_value: 1b7dccfb-762c-4d3b-954a-aa0ba9a38752
|
|
- *id001
|
|
- *id002
|
|
provenance:
|
|
data_source: CONVERSATION_NLP
|
|
data_tier: TIER_4_INFERRED
|
|
extraction_date: '2025-11-06T08:25:13.555410+00:00'
|
|
extraction_method: 'Created from CH-Annotator file: latin_american_institutions_AUTHORITATIVE_ch_annotator.yaml'
|
|
confidence_score: 0.7
|
|
ch_annotator:
|
|
convention_id: ch_annotator-v1_7_0
|
|
convention_version: 1.7.0
|
|
entity_classification:
|
|
hypernym: GRP
|
|
hypernym_label: GROUP
|
|
subtype: GRP.EDU
|
|
subtype_label: EDUCATION_PROVIDER
|
|
ontology_class: schema:EducationalOrganization
|
|
alternative_classes:
|
|
- org:FormalOrganization
|
|
- rov:RegisteredOrganization
|
|
- glam:HeritageCustodian
|
|
extraction_provenance:
|
|
namespace: glam
|
|
path: /conversations/2025-09-22T14-40-15-0102c00a-4c0a-4488-bdca-5dd9fb94c9c5
|
|
timestamp: '2025-11-06T08:25:13.555410+00:00'
|
|
agent: claude-conversation
|
|
context_convention: ch_annotator-v1_7_0
|
|
annotation_provenance:
|
|
annotation_agent: opencode-claude-sonnet-4
|
|
annotation_date: '2025-12-06T21:13:56.173868+00:00'
|
|
annotation_method: retroactive CH-Annotator application via batch script
|
|
source_file: latin_american_institutions_AUTHORITATIVE.yaml
|
|
annotation_metadata:
|
|
confidence_score: 0.7
|
|
verified: false
|
|
verification_date: null
|
|
verified_by: null
|
|
entity_claims:
|
|
- claim_type: full_name
|
|
claim_value: USP/UNICAMP/UNESP
|
|
property_uri: skos:prefLabel
|
|
provenance:
|
|
namespace: glam
|
|
path: /conversations/2025-09-22T14-40-15-0102c00a-4c0a-4488-bdca-5dd9fb94c9c5
|
|
timestamp: '2025-11-06T08:25:13.555410+00:00'
|
|
agent: claude-conversation
|
|
context_convention: ch_annotator-v1_7_0
|
|
confidence: 0.7
|
|
- claim_type: institution_type
|
|
claim_value: EDUCATION_PROVIDER
|
|
property_uri: rdf:type
|
|
provenance:
|
|
namespace: glam
|
|
path: /conversations/2025-09-22T14-40-15-0102c00a-4c0a-4488-bdca-5dd9fb94c9c5
|
|
timestamp: '2025-11-06T08:25:13.555410+00:00'
|
|
agent: claude-conversation
|
|
context_convention: ch_annotator-v1_7_0
|
|
confidence: 0.95
|
|
- claim_type: ghcid
|
|
claim_value: BR-SP-XXX-E-U
|
|
property_uri: glam:ghcid
|
|
provenance:
|
|
namespace: glam
|
|
path: /conversations/2025-09-22T14-40-15-0102c00a-4c0a-4488-bdca-5dd9fb94c9c5
|
|
timestamp: '2025-11-06T08:25:13.555410+00:00'
|
|
agent: claude-conversation
|
|
context_convention: ch_annotator-v1_7_0
|
|
confidence: 1.0
|
|
integration_note:
|
|
created_from: latin_american_institutions_AUTHORITATIVE_ch_annotator.yaml
|
|
creation_date: '2025-12-06T23:35:51.996651+00:00'
|
|
creation_method: create_custodian_from_ch_annotator.py
|
|
google_maps_enrichment:
|
|
place_id: ChIJtU3SBbDGyJQRltcEzw5128Y
|
|
formatted_address: Cidade Universitária Zeferino Vaz - Barão Geraldo, Campinas -
|
|
SP, 13083-970, Brazil
|
|
website: http://www.unicamp.br/
|
|
latitude: -22.818439299999998
|
|
longitude: -47.0647206
|
|
enriched_at: '2025-12-07T16:39:12.242790+00:00'
|
|
source: Google Places API (New)
|