glam/data/custodian/BR-RJ-RDJ-A-DA-deap_archives.yaml
kempersc 1e01639c56 fix(data): resolve XXX placeholder city codes to actual GeoNames settlements
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}
2025-12-07 17:47:09 +01:00

155 lines
5.7 KiB
YAML

original_entry:
name: DEAP Archives
institution_type: ARCHIVE
source: CH-Annotator (latin_american_institutions_AUTHORITATIVE_ch_annotator.yaml)
identifiers:
- identifier_scheme: GHCID
identifier_value: BR-PR-XXX-A-DA
- identifier_scheme: GHCID_NUMERIC
identifier_value: '10990438986336437798'
- &id001
identifier_scheme: OLD_ID
identifier_value: https://w3id.org/heritage/custodian/br/deap-archives
- identifier_scheme: GHCID_UUID
identifier_value: b52c7eaf-4a32-56ca-88bd-f4d1c37d8231
identifier_url: urn:uuid:b52c7eaf-4a32-56ca-88bd-f4d1c37d8231
- identifier_scheme: GHCID_UUID_SHA256
identifier_value: 9885e207-3a30-8626-ba7d-7bab5ce630d3
identifier_url: urn:uuid:9885e207-3a30-8626-ba7d-7bab5ce630d3
- identifier_scheme: RECORD_ID
identifier_value: 019a58fd-3226-7f60-9aa3-e03a3339296d
identifier_url: urn:uuid:019a58fd-3226-7f60-9aa3-e03a3339296d
- &id002
identifier_scheme: OLD_ID
identifier_value: 10990438986336437798
locations:
- country: BR
region: PARANÁ
processing_timestamp: '2025-12-06T23:39:01.708973+00:00'
ghcid:
ghcid_current: BR-RJ-RDJ-A-DA-deap_archives
ghcid_original: BR-PA-XXX-A-DA-deap_archives
ghcid_uuid: d3542b1f-1899-5211-8ef3-e47606a7c5db
ghcid_uuid_sha256: c8cf24d5-b7db-8495-429d-b7b508c75d03
ghcid_numeric: 14469824628095935637
record_id: 93d28bd6-0570-4f81-8b51-d695c0e3646b
generation_timestamp: '2025-12-06T23:39:01.708973+00:00'
location_resolution:
method: GOOGLE_PLACES_GEONAMES
country_code: BR
region_code: RJ
region_name: Rio de Janeiro
city_code: RDJ
city_name: Rio de Janeiro
geonames_id: 3451190
feature_code: PPLA
google_place_id: ChIJe9cDTGp_mQARQb9bmMSDOiA
latitude: -22.9064403
longitude: -43.1906794
resolution_date: '2025-12-07T16:38:58.777124+00:00'
ghcid_history:
- ghcid: BR-PA-XXX-A-DA-deap_archives
ghcid_numeric: 14469824628095935637
valid_from: '2025-12-06T23:39:01.708973+00:00'
reason: Initial GHCID from CH-Annotator (latin_american_institutions_AUTHORITATIVE_ch_annotator.yaml)
valid_to: '2025-12-07T16:38:58.777124+00:00'
- ghcid: BR-RJ-RDJ-A-DA-deap_archives
ghcid_numeric: 14469824628095935637
valid_from: '2025-12-07T16:38:58.777124+00:00'
reason: 'Location resolved via Google Places + GeoNames: Rio de Janeiro (RJ)'
custodian_name:
claim_type: custodian_name
claim_value: DEAP Archives
source_type: ch_annotator
identifiers:
- identifier_scheme: GHCID
identifier_value: BR-RJ-RDJ-A-DA-deap_archives
- identifier_scheme: GHCID_UUID
identifier_value: d3542b1f-1899-5211-8ef3-e47606a7c5db
- identifier_scheme: GHCID_UUID_SHA256
identifier_value: c8cf24d5-b7db-8495-429d-b7b508c75d03
- identifier_scheme: GHCID_NUMERIC
identifier_value: '14469824628095935637'
- identifier_scheme: RECORD_ID
identifier_value: 93d28bd6-0570-4f81-8b51-d695c0e3646b
- *id001
- *id002
provenance:
data_source: CONVERSATION_NLP
data_tier: TIER_4_INFERRED
extraction_date: '2025-11-06T08:25:13.555352+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.HER.ARC
subtype_label: ARCHIVE
ontology_class: schema:ArchiveOrganization
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: '2025-11-06T08:25:13.555352+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: DEAP Archives
property_uri: skos:prefLabel
provenance:
namespace: glam
path: /conversations/2025-09-22T14-40-15-0102c00a-4c0a-4488-bdca-5dd9fb94c9c5
timestamp: '2025-11-06T08:25:13.555352+00:00'
agent: claude-conversation
context_convention: ch_annotator-v1_7_0
confidence: 0.7
- claim_type: institution_type
claim_value: ARCHIVE
property_uri: rdf:type
provenance:
namespace: glam
path: /conversations/2025-09-22T14-40-15-0102c00a-4c0a-4488-bdca-5dd9fb94c9c5
timestamp: '2025-11-06T08:25:13.555352+00:00'
agent: claude-conversation
context_convention: ch_annotator-v1_7_0
confidence: 0.95
- claim_type: ghcid
claim_value: BR-PR-XXX-A-DA
property_uri: glam:ghcid
provenance:
namespace: glam
path: /conversations/2025-09-22T14-40-15-0102c00a-4c0a-4488-bdca-5dd9fb94c9c5
timestamp: '2025-11-06T08:25:13.555352+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: '2025-12-06T23:39:01.708973+00:00'
creation_method: create_custodian_from_ch_annotator.py
google_maps_enrichment:
place_id: ChIJe9cDTGp_mQARQb9bmMSDOiA
formatted_address: Praça da República, 173 - Centro, Rio de Janeiro - RJ, 20211-350,
Brazil
website: http://www.arquivonacional.gov.br/
latitude: -22.9064403
longitude: -43.1906794
enriched_at: '2025-12-07T16:38:58.777124+00:00'
source: Google Places API (New)