175 lines
6.7 KiB
YAML
175 lines
6.7 KiB
YAML
original_entry:
|
|
name: Státní okresní archiv Praha-venkov se sídlem v Dobřichovicích
|
|
institution_type: ARCHIVE
|
|
source: CH-Annotator (czech_unified_ch_annotator.yaml)
|
|
identifiers:
|
|
- &id001
|
|
identifier_scheme: ARON_UUID
|
|
identifier_value: 29feb0f1-de87-49ba-a805-74546f0cbd5c
|
|
identifier_url: https://portal.nacr.cz/aron/apu/29feb0f1-de87-49ba-a805-74546f0cbd5c
|
|
- &id002
|
|
identifier_scheme: INSTITUTION_CODE
|
|
identifier_value: '221250010'
|
|
locations: []
|
|
processing_timestamp: '2025-12-06T23:37:43.939804+00:00'
|
|
ghcid:
|
|
ghcid_current: CZ-10-PRK-A-SOAPVSSVD
|
|
ghcid_original: XX-XX-XXX-A-SOAPVSSVD
|
|
ghcid_uuid: 586553e0-07d1-5ce8-a4ea-36857e879562
|
|
ghcid_uuid_sha256: a23edee3-1b53-8b45-485b-9ed96c08a68f
|
|
ghcid_numeric: 11691026749697776453
|
|
record_id: 7fdf846a-57b5-429b-aa4d-042453081c3d
|
|
generation_timestamp: '2025-12-06T23:37:43.939804+00:00'
|
|
location_resolution:
|
|
country_code: CZ
|
|
region_code: '10'
|
|
city_code: PRK
|
|
method: CH_ANNOTATOR_TOP_SET
|
|
resolution_timestamp: '2025-12-07T00:19:30.011768+00:00'
|
|
city_name: Praha Klanovice
|
|
geonames_id: 8629195
|
|
feature_code: PPL
|
|
extracted_toponym: Praha
|
|
latitude: 50.0974
|
|
longitude: 14.66915
|
|
ghcid_history:
|
|
- previous_ghcid_component: "PK"
|
|
new_ghcid_component: "PRK"
|
|
change_date: "2025-12-20T19:55:24Z"
|
|
reason: "Fixed 2-letter city code to proper 3-letter code per AGENTS.md. City: Praha Klanovice"
|
|
- ghcid: XX-XX-XXX-A-SOAPVSSVD
|
|
ghcid_numeric: 11691026749697776453
|
|
valid_from: '2025-12-06T23:37:43.939804+00:00'
|
|
reason: Initial GHCID from CH-Annotator (czech_unified_ch_annotator.yaml)
|
|
- ghcid: CZ-XX-XXX-A-SOAPVSSVD
|
|
valid_from: '2025-12-06T23:56:12.090246+00:00'
|
|
reason: 'Country resolved via Wikidata P17: XX→CZ'
|
|
- ghcid: CZ-10-PK-A-SOAPVSSVD
|
|
valid_from: '2025-12-07T00:19:30.011774+00:00'
|
|
reason: 'Location resolved via CH-Annotator TOP.SET extraction: Praha -> Praha Klanovice (GeoNames:8629195)'
|
|
custodian_name:
|
|
claim_type: custodian_name
|
|
claim_value: Státní okresní archiv Praha-venkov se sídlem v Dobřichovicích
|
|
source_type: ch_annotator
|
|
identifiers:
|
|
- identifier_scheme: GHCID
|
|
identifier_value: XX-XX-XXX-A-SOAPVSSVD
|
|
- identifier_scheme: GHCID_UUID
|
|
identifier_value: 586553e0-07d1-5ce8-a4ea-36857e879562
|
|
- identifier_scheme: GHCID_UUID_SHA256
|
|
identifier_value: a23edee3-1b53-8b45-485b-9ed96c08a68f
|
|
- identifier_scheme: GHCID_NUMERIC
|
|
identifier_value: '11691026749697776453'
|
|
- identifier_scheme: RECORD_ID
|
|
identifier_value: 7fdf846a-57b5-429b-aa4d-042453081c3d
|
|
- *id001
|
|
- *id002
|
|
provenance:
|
|
data_source: API_SCRAPING
|
|
data_tier: TIER_1_AUTHORITATIVE
|
|
extraction_date: '2025-11-19T11:35:45.743760+00:00'
|
|
extraction_method: 'Created from CH-Annotator file: czech_unified_ch_annotator.yaml'
|
|
confidence_score: 0.85
|
|
notes:
|
|
- 'Country resolved 2025-12-06T23:56:12Z: XX→CZ via Wikidata P17'
|
|
- 'Location resolved 2025-12-07T00:19:30Z: CH-Annotator TOP.SET extraction ''Praha'' -> Praha Klanovice (GeoNames:8629195,
|
|
Region:10)'
|
|
- 'YouTube/Google Maps enrichment 2025-12-08T19:45:25Z: Maps: rejected by LLM; YouTube: not found'
|
|
- Canonical location added via normalize_custodian_files.py on 2025-12-08T23:11:18Z
|
|
- Canonical location added via normalize_custodian_files.py on 2025-12-08T23:48:03Z
|
|
- Canonical location added via normalize_custodian_files.py on 2025-12-09T06:49:27Z
|
|
ch_annotator:
|
|
convention_id: ch_annotator-v1_7_0
|
|
convention_version: 1.7.0
|
|
entity_classification:
|
|
hypernym: GRP
|
|
hypernym_label: GROUP
|
|
subtype: GRP.HER.ARC
|
|
subtype_label: ARCHIVE
|
|
ontology_class: schema:ArchiveOrganization
|
|
alternative_classes:
|
|
- org:FormalOrganization
|
|
- rov:RegisteredOrganization
|
|
- glam:HeritageCustodian
|
|
extraction_provenance:
|
|
namespace: glam
|
|
path: /files/czech_unified.yaml
|
|
timestamp: '2025-11-19T11:35:45.743760+00:00'
|
|
agent: claude-conversation
|
|
context_convention: ch_annotator-v1_7_0
|
|
annotation_provenance:
|
|
annotation_agent: opencode-claude-sonnet-4
|
|
annotation_date: '2025-12-06T21:12:32.389491+00:00'
|
|
annotation_method: retroactive CH-Annotator application via batch script
|
|
source_file: czech_unified.yaml
|
|
annotation_metadata:
|
|
confidence_score: 0.85
|
|
verified: false
|
|
verification_date: null
|
|
verified_by: null
|
|
entity_claims:
|
|
- claim_type: full_name
|
|
claim_value: Státní okresní archiv Praha-venkov se sídlem v Dobřichovicích
|
|
property_uri: skos:prefLabel
|
|
provenance:
|
|
namespace: glam
|
|
path: /files/czech_unified.yaml
|
|
timestamp: '2025-11-19T11:35:45.743760+00:00'
|
|
agent: claude-conversation
|
|
context_convention: ch_annotator-v1_7_0
|
|
confidence: 0.85
|
|
- claim_type: institution_type
|
|
claim_value: ARCHIVE
|
|
property_uri: rdf:type
|
|
provenance:
|
|
namespace: glam
|
|
path: /files/czech_unified.yaml
|
|
timestamp: '2025-11-19T11:35:45.743760+00:00'
|
|
agent: claude-conversation
|
|
context_convention: ch_annotator-v1_7_0
|
|
confidence: 0.95
|
|
- claim_type: location_settlement
|
|
claim_value: Praha Klanovice
|
|
property_uri: schema:location
|
|
hypernym_code: TOP.SET
|
|
hypernym_label: SETTLEMENT
|
|
provenance:
|
|
namespace: geonames
|
|
path: /geonames/8629195
|
|
timestamp: '2025-12-07T00:19:30.011777+00:00'
|
|
agent: extract_locations_ch_annotator.py
|
|
context_convention: ch_annotator-v1_7_0
|
|
confidence: 0.85
|
|
extraction_source:
|
|
field: institution_name
|
|
extracted_text: Praha
|
|
method: pattern_matching
|
|
integration_note:
|
|
created_from: czech_unified_ch_annotator.yaml
|
|
creation_date: '2025-12-06T23:37:43.939804+00:00'
|
|
creation_method: create_custodian_from_ch_annotator.py
|
|
google_maps_status: NO_MATCH
|
|
google_maps_rejected:
|
|
candidate_name: State Regional Archives in Prague
|
|
rejection_reason: The candidate is a heritage institution (GRP.HER) and the name is a potential English translation, but
|
|
there is a significant location mismatch. The source city is Praha Klanovice, while the candidate is in Praha 4-Chodov.
|
|
These are distinct districts in Prague, indicating they are not the same institution.
|
|
timestamp: '2025-12-08T19:45:25.593331+00:00'
|
|
youtube_status: NOT_FOUND
|
|
youtube_search_query: Státní okresní archiv Praha-venkov se sídlem v Dobřichovicích official
|
|
youtube_search_timestamp: '2025-12-08T19:45:25.939581+00:00'
|
|
location:
|
|
latitude: 50.0974
|
|
longitude: 14.66915
|
|
coordinate_provenance:
|
|
source_type: GHCID_RESOLUTION_DIRECT
|
|
source_path: ghcid.location_resolution
|
|
original_timestamp: '2025-12-07T00:19:30.011768+00:00'
|
|
entity_id: 8629195
|
|
resolution_method: CH_ANNOTATOR_TOP_SET
|
|
city: Praha Klanovice
|
|
region_code: '10'
|
|
country: CZ
|
|
geonames_id: 8629195
|
|
feature_code: PPL
|
|
normalization_timestamp: '2025-12-09T06:49:27.658603+00:00'
|