glam/data/custodian/CZ-31-STR-A-SOAS.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

172 lines
5.9 KiB
YAML

original_entry:
name: Státní okresní archiv Strakonice
institution_type: ARCHIVE
source: CH-Annotator (czech_unified_ch_annotator.yaml)
identifiers:
- &id001
identifier_scheme: ARON_UUID
identifier_value: 508a3dfa-b147-46bf-a245-d1b033f1739b
identifier_url: https://portal.nacr.cz/aron/apu/508a3dfa-b147-46bf-a245-d1b033f1739b
- &id002
identifier_scheme: INSTITUTION_CODE
identifier_value: '222106010'
- &id003
identifier_scheme: Wikidata
identifier_value: Q54685096
identifier_url: https://www.wikidata.org/wiki/Q54685096
- &id004
identifier_scheme: VIAF
identifier_value: '148240883'
identifier_url: https://viaf.org/viaf/148240883
locations: []
processing_timestamp: '2025-12-06T23:37:44.120742+00:00'
ghcid:
ghcid_current: CZ-31-STR-A-SOAS
ghcid_original: XX-XX-XXX-A-SOAS
ghcid_uuid: 720a8fbf-6551-5806-9aa2-9f6fb67e12f8
ghcid_uuid_sha256: f9c0c65c-0ce8-8508-8251-63940898e18f
ghcid_numeric: 17996602209628386568
record_id: d7fef66e-c646-45b0-886a-69d2d7bbd606
generation_timestamp: '2025-12-06T23:37:44.120742+00:00'
location_resolution:
country_code: CZ
region_code: '31'
city_code: STR
method: CH_ANNOTATOR_TOP_SET
resolution_timestamp: '2025-12-07T00:20:05.489647+00:00'
region_name: CZ-31
iso_code_source: CZ-31
city_name: Strakonice
geonames_id: 3065067
feature_code: PPL
extracted_toponym: Strakonice
latitude: 49.26141
longitude: 13.90237
ghcid_history:
- ghcid: XX-XX-XXX-A-SOAS
ghcid_numeric: 17996602209628386568
valid_from: '2025-12-06T23:37:44.120742+00:00'
reason: Initial GHCID from CH-Annotator (czech_unified_ch_annotator.yaml)
- ghcid: CZ-XX-XXX-A-SOAS
valid_from: '2025-12-06T23:54:39.694522+00:00'
reason: 'Country resolved via Wikidata P17: XX→CZ'
- ghcid: CZ-31-XXX-A-SOAS
valid_from: '2025-12-07T00:00:25.795679+00:00'
reason: 'Region resolved via Wikidata P131: XX->31 (CZ-31)'
- ghcid: CZ-31-STR-A-SOAS
valid_from: '2025-12-07T00:20:05.489657+00:00'
reason: 'Location resolved via CH-Annotator TOP.SET extraction: Strakonice ->
Strakonice (GeoNames:3065067)'
custodian_name:
claim_type: custodian_name
claim_value: Státní okresní archiv Strakonice
source_type: ch_annotator
identifiers:
- identifier_scheme: GHCID
identifier_value: XX-XX-XXX-A-SOAS
- identifier_scheme: GHCID_UUID
identifier_value: 720a8fbf-6551-5806-9aa2-9f6fb67e12f8
- identifier_scheme: GHCID_UUID_SHA256
identifier_value: f9c0c65c-0ce8-8508-8251-63940898e18f
- identifier_scheme: GHCID_NUMERIC
identifier_value: '17996602209628386568'
- identifier_scheme: RECORD_ID
identifier_value: d7fef66e-c646-45b0-886a-69d2d7bbd606
- *id001
- *id002
- *id003
- *id004
provenance:
data_source: API_SCRAPING
data_tier: TIER_1_AUTHORITATIVE
extraction_date: '2025-11-19T11:35:45.744070+00:00'
extraction_method: 'Created from CH-Annotator file: czech_unified_ch_annotator.yaml'
confidence_score: 0.85
notes:
- 'Country resolved 2025-12-06T23:54:39Z: XX→CZ via Wikidata P17'
- 'Region resolved 2025-12-07T00:00:25Z: XX->31 via Wikidata P131 (CZ-31)'
- 'Location resolved 2025-12-07T00:20:05Z: CH-Annotator TOP.SET extraction ''Strakonice''
-> Strakonice (GeoNames:3065067, Region:31)'
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: '2025-11-19T11:35:45.744070+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 Strakonice
property_uri: skos:prefLabel
provenance:
namespace: glam
path: /files/czech_unified.yaml
timestamp: '2025-11-19T11:35:45.744070+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: '2025-11-19T11:35:45.744070+00:00'
agent: claude-conversation
context_convention: ch_annotator-v1_7_0
confidence: 0.95
- claim_type: wikidata_id
claim_value: Q54685096
property_uri: owl:sameAs
provenance:
namespace: wikidata
path: /entity/Q54685096
timestamp: '2025-11-19T11:35:45.744070+00:00'
agent: claude-conversation
context_convention: ch_annotator-v1_7_0
confidence: 0.98
- claim_type: location_settlement
claim_value: Strakonice
property_uri: schema:location
hypernym_code: TOP.SET
hypernym_label: SETTLEMENT
provenance:
namespace: geonames
path: /geonames/3065067
timestamp: '2025-12-07T00:20:05.489661+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: Strakonice
method: pattern_matching
integration_note:
created_from: czech_unified_ch_annotator.yaml
creation_date: '2025-12-06T23:37:44.120742+00:00'
creation_method: create_custodian_from_ch_annotator.py
wikidata_enrichment:
wikidata_entity_id: Q54685096
wikidata_label_en: Státní okresní archiv Strakonice