glam/data/custodian/MX-BA-XXX-X-ISC.yaml
kempersc f284e87d13 feat: add 24,963 heritage custodian records from global extraction
Major batch addition of heritage institution data:
- Japan: 12,077 institutions (libraries, museums, archives)
- Czechia: 6,760 institutions
- Switzerland: 2,390 institutions
- Belgium: 448 institutions
- Belarus: 257 institutions
- Austria: 249 institutions (with corrected GHCIDs)
- Argentina: 235 institutions (bibliotecas populares)
- Brazil: 155 institutions
- Mexico: 110 institutions
- Bulgaria: 98 institutions
- Chile: 83 institutions
- Egypt: 50 institutions
- And additional records from VN, NL, GE, KR, GB, FR, US, IN, etc.

All records include:
- Standardized GHCID identifiers (alphabetic-only abbreviations)
- GeoNames-resolved location data
- ISO 3166-2 region codes
- Provenance metadata with extraction timestamps
2025-12-07 14:24:48 +01:00

138 lines
4.8 KiB
YAML

original_entry:
name: Instituto Sudcaliforniano de Cultura
institution_type: MIXED
source: CH-Annotator (latin_american_institutions_AUTHORITATIVE_ch_annotator.yaml)
identifiers:
- &id001
identifier_scheme: Website
identifier_value: https://culturabcs.gob.mx/
identifier_url: https://culturabcs.gob.mx/
- identifier_scheme: GHCID
identifier_value: MX-BCS-XXX-M-ISC
- identifier_scheme: GHCID_NUMERIC
identifier_value: '17130207555014018408'
- &id002
identifier_scheme: OLD_ID
identifier_value: https://w3id.org/heritage/custodian/mx/m-instituto-sudcaliforniano-de-c-0006
- identifier_scheme: GHCID_UUID
identifier_value: a8d5ea5e-e81b-5c34-97a5-aa8af568f017
identifier_url: urn:uuid:a8d5ea5e-e81b-5c34-97a5-aa8af568f017
- identifier_scheme: GHCID_UUID_SHA256
identifier_value: edbab902-f552-8568-acaa-89e2157fbd90
identifier_url: urn:uuid:edbab902-f552-8568-acaa-89e2157fbd90
- identifier_scheme: RECORD_ID
identifier_value: 019a58fd-3228-7854-ade2-8ec02f6bd656
identifier_url: urn:uuid:019a58fd-3228-7854-ade2-8ec02f6bd656
- &id003
identifier_scheme: OLD_ID
identifier_value: 17130207555014018408
locations:
- region: BAJA CALIFORNIA SUR
country: MX
processing_timestamp: '2025-12-06T23:39:02.032033+00:00'
ghcid:
ghcid_current: MX-BA-XXX-X-ISC
ghcid_original: MX-BA-XXX-X-ISC
ghcid_uuid: bf07b3dc-1862-505a-87da-d8159094322a
ghcid_uuid_sha256: 3e263639-0ffc-8642-3f51-4b8b12901a10
ghcid_numeric: 4478326498175759938
record_id: 5e45943b-76fe-42b3-997c-26de623b367a
generation_timestamp: '2025-12-06T23:39:02.032033+00:00'
location_resolution:
country_code: MX
region_code: BA
city_code: XXX
method: CH_ANNOTATOR_SOURCE
ghcid_history:
- ghcid: MX-BA-XXX-X-ISC
ghcid_numeric: 4478326498175759938
valid_from: '2025-12-06T23:39:02.032033+00:00'
reason: Initial GHCID from CH-Annotator (latin_american_institutions_AUTHORITATIVE_ch_annotator.yaml)
custodian_name:
claim_type: custodian_name
claim_value: Instituto Sudcaliforniano de Cultura
source_type: ch_annotator
identifiers:
- identifier_scheme: GHCID
identifier_value: MX-BA-XXX-X-ISC
- identifier_scheme: GHCID_UUID
identifier_value: bf07b3dc-1862-505a-87da-d8159094322a
- identifier_scheme: GHCID_UUID_SHA256
identifier_value: 3e263639-0ffc-8642-3f51-4b8b12901a10
- identifier_scheme: GHCID_NUMERIC
identifier_value: '4478326498175759938'
- identifier_scheme: RECORD_ID
identifier_value: 5e45943b-76fe-42b3-997c-26de623b367a
- *id001
- *id002
- *id003
provenance:
data_source: CONVERSATION_NLP
data_tier: TIER_4_INFERRED
extraction_date: '2025-11-06T07:54:59.620408+00:00'
extraction_method: 'Created from CH-Annotator file: latin_american_institutions_AUTHORITATIVE_ch_annotator.yaml'
confidence_score: 0.9
ch_annotator:
convention_id: ch_annotator-v1_7_0
convention_version: 1.7.0
entity_classification:
hypernym: GRP
hypernym_label: GROUP
subtype: GRP.HER.MIX
subtype_label: MIXED
ontology_class: glam:HeritageCustodian
alternative_classes:
- org:FormalOrganization
- rov:RegisteredOrganization
- glam:HeritageCustodian
extraction_provenance:
namespace: glam
path: /conversations/mixed
timestamp: '2025-11-06T07:54:59.620408+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: 0.9
verified: false
verification_date: null
verified_by: null
entity_claims:
- claim_type: full_name
claim_value: Instituto Sudcaliforniano de Cultura
property_uri: skos:prefLabel
provenance:
namespace: glam
path: /conversations/mixed
timestamp: '2025-11-06T07:54:59.620408+00:00'
agent: claude-conversation
context_convention: ch_annotator-v1_7_0
confidence: 0.9
- claim_type: institution_type
claim_value: MIXED
property_uri: rdf:type
provenance:
namespace: glam
path: /conversations/mixed
timestamp: '2025-11-06T07:54:59.620408+00:00'
agent: claude-conversation
context_convention: ch_annotator-v1_7_0
confidence: 0.95
- claim_type: ghcid
claim_value: MX-BCS-XXX-M-ISC
property_uri: glam:ghcid
provenance:
namespace: glam
path: /conversations/mixed
timestamp: '2025-11-06T07:54:59.620408+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: '2025-12-06T23:39:02.032033+00:00'
creation_method: create_custodian_from_ch_annotator.py