208 lines
7.7 KiB
YAML
208 lines
7.7 KiB
YAML
original_entry:
|
|
name: Zahraniční instituce
|
|
institution_type: ARCHIVE
|
|
source: CH-Annotator (czech_unified_ch_annotator.yaml)
|
|
identifiers:
|
|
- &id001
|
|
identifier_scheme: ARON_UUID
|
|
identifier_value: 052d0d6f-1bb7-434b-96d5-1894b571effe
|
|
identifier_url: https://portal.nacr.cz/aron/apu/052d0d6f-1bb7-434b-96d5-1894b571effe
|
|
- &id002
|
|
identifier_scheme: INSTITUTION_CODE
|
|
identifier_value: 009999010
|
|
locations: []
|
|
processing_timestamp: '2025-12-06T23:37:43.727774+00:00'
|
|
ghcid:
|
|
ghcid_current: CZ-10-PRA-A-ZI
|
|
ghcid_original: XX-XX-XXX-A-ZI
|
|
ghcid_uuid: 72d33847-768e-5d26-bf02-8b579d7a4d97
|
|
ghcid_uuid_sha256: 974f6f73-8f8f-8be0-e054-e8c21440599a
|
|
ghcid_numeric: 10903055765007735776
|
|
record_id: 0407a140-a828-4fb9-8991-58a1557c2a10
|
|
generation_timestamp: '2025-12-06T23:37:43.727774+00:00'
|
|
location_resolution:
|
|
method: GEONAMES_RESEARCH
|
|
country_code: CZ
|
|
region_code: '10'
|
|
region_name: Prague
|
|
city_code: PRA
|
|
city_name: Prague
|
|
geonames_id: 3067696
|
|
admin1_code: '52'
|
|
resolution_timestamp: '2025-12-07T12:54:27.635684+00:00'
|
|
research_date: '2025-12-07'
|
|
research_method: GeoNames database + web search verification
|
|
ghcid_history:
|
|
- ghcid: XX-XX-XXX-A-ZI
|
|
ghcid_numeric: 10903055765007735776
|
|
valid_from: '2025-12-06T23:37:43.727774+00:00'
|
|
reason: Initial GHCID from CH-Annotator (czech_unified_ch_annotator.yaml)
|
|
- ghcid: CZ-XX-XXX-A-ZI
|
|
valid_from: '2025-12-06T23:56:12.319555+00:00'
|
|
reason: 'Country resolved via Wikidata P17: XX→CZ'
|
|
- ghcid: CZ-10-PRA-A-ZI
|
|
valid_from: '2025-12-07T12:54:27.635684+00:00'
|
|
reason: 'Region resolved via GeoNames research: XX→10, city: Prague (GeoNames ID: 3067696)'
|
|
custodian_name:
|
|
claim_type: custodian_name
|
|
claim_value: Zahraniční instituce
|
|
source_type: ch_annotator
|
|
identifiers:
|
|
- identifier_scheme: GHCID
|
|
identifier_value: XX-XX-XXX-A-ZI
|
|
- identifier_scheme: GHCID_UUID
|
|
identifier_value: 72d33847-768e-5d26-bf02-8b579d7a4d97
|
|
- identifier_scheme: GHCID_UUID_SHA256
|
|
identifier_value: 974f6f73-8f8f-8be0-e054-e8c21440599a
|
|
- identifier_scheme: GHCID_NUMERIC
|
|
identifier_value: '10903055765007735776'
|
|
- identifier_scheme: RECORD_ID
|
|
identifier_value: 0407a140-a828-4fb9-8991-58a1557c2a10
|
|
- *id001
|
|
- *id002
|
|
provenance:
|
|
data_source: API_SCRAPING
|
|
data_tier: TIER_1_AUTHORITATIVE
|
|
extraction_date: '2025-11-19T11:35:45.743292+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'
|
|
- 'Region resolved 2025-12-07: XX→CZ-10 (Prague) via GeoNames research'
|
|
- 'YouTube/Google Maps enrichment 2025-12-08T19:48:51Z: Maps: rejected by LLM; YouTube: not found'
|
|
- Canonical location added via normalize_custodian_files.py on 2025-12-08T23:11:19Z
|
|
- Canonical location added via normalize_custodian_files.py on 2025-12-08T23:48:05Z
|
|
- Canonical location added via normalize_custodian_files.py on 2025-12-09T06:49:29Z
|
|
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
|
|
agent: batch-script-create-custodian-from-ch-annotator
|
|
context_convention: ch_annotator-v1_7_0
|
|
source_archived_at: '2025-11-19T11:35:45.743292+00:00'
|
|
statement_created_at: '2025-12-06T21:12:32.389491+00:00'
|
|
source_type: library_registry_api
|
|
migration_note: Migrated from agent:claude-conversation on 2025-12-30
|
|
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: Zahraniční instituce
|
|
property_uri: skos:prefLabel
|
|
provenance:
|
|
namespace: glam
|
|
path: /files/czech_unified.yaml
|
|
agent: batch-script-create-custodian-from-ch-annotator
|
|
context_convention: ch_annotator-v1_7_0
|
|
source_archived_at: '2025-11-19T11:35:45.743292+00:00'
|
|
statement_created_at: '2025-12-06T21:12:32.389491+00:00'
|
|
source_type: library_registry_api
|
|
migration_note: Migrated from agent:claude-conversation on 2025-12-30
|
|
confidence: 0.85
|
|
- claim_type: institution_type
|
|
claim_value: ARCHIVE
|
|
property_uri: rdf:type
|
|
provenance:
|
|
namespace: glam
|
|
path: /files/czech_unified.yaml
|
|
agent: batch-script-create-custodian-from-ch-annotator
|
|
context_convention: ch_annotator-v1_7_0
|
|
source_archived_at: '2025-11-19T11:35:45.743292+00:00'
|
|
statement_created_at: '2025-12-06T21:12:32.389491+00:00'
|
|
source_type: library_registry_api
|
|
migration_note: Migrated from agent:claude-conversation on 2025-12-30
|
|
confidence: 0.95
|
|
- claim_type: location_city
|
|
claim_value: Prague
|
|
property_uri: schema:addressLocality
|
|
provenance:
|
|
namespace: geonames
|
|
path: /cities/3067696/name
|
|
timestamp: '2025-12-07T12:54:27.635684+00:00'
|
|
agent: glm4.6
|
|
context_convention: ch_annotator-v1_7_0
|
|
confidence: 0.95
|
|
resolution_method: GEONAMES_RESEARCH
|
|
- claim_type: location_region
|
|
claim_value: Prague
|
|
property_uri: schema:addressRegion
|
|
provenance:
|
|
namespace: geonames
|
|
path: /cities/3067696/admin1
|
|
timestamp: '2025-12-07T12:54:27.635684+00:00'
|
|
agent: glm4.6
|
|
context_convention: ch_annotator-v1_7_0
|
|
confidence: 0.95
|
|
resolution_method: GEONAMES_RESEARCH
|
|
- claim_type: location_country
|
|
claim_value: CZ
|
|
property_uri: schema:addressCountry
|
|
provenance:
|
|
namespace: geonames
|
|
path: /cities/3067696/country
|
|
timestamp: '2025-12-07T12:54:27.635684+00:00'
|
|
agent: glm4.6
|
|
context_convention: ch_annotator-v1_7_0
|
|
confidence: 0.98
|
|
resolution_method: GEONAMES_RESEARCH
|
|
- claim_type: geonames_id
|
|
claim_value: '3067696'
|
|
property_uri: gn:geonamesId
|
|
provenance:
|
|
namespace: geonames
|
|
path: /cities/3067696
|
|
timestamp: '2025-12-07T12:54:27.635684+00:00'
|
|
agent: glm4.6
|
|
context_convention: ch_annotator-v1_7_0
|
|
confidence: 0.98
|
|
resolution_method: GEONAMES_RESEARCH
|
|
integration_note:
|
|
created_from: czech_unified_ch_annotator.yaml
|
|
creation_date: '2025-12-06T23:37:43.727774+00:00'
|
|
creation_method: create_custodian_from_ch_annotator.py
|
|
location:
|
|
city: Prague
|
|
region: Prague
|
|
region_code: '10'
|
|
country: CZ
|
|
geonames_id: 3067696
|
|
normalization_timestamp: '2025-12-09T15:34:40.331375+00:00'
|
|
latitude: 50.08804
|
|
longitude: 14.42076
|
|
coordinate_provenance:
|
|
source_type: GEONAMES_LOCAL
|
|
source_path: data/reference/geonames.db
|
|
entity_id: 3067696
|
|
original_timestamp: '2025-12-09T15:34:40.331355+00:00'
|
|
geonames_name: Prague
|
|
feature_code: PPLC
|
|
google_maps_status: NO_MATCH
|
|
google_maps_rejected:
|
|
candidate_name: Czech National Agency for International Education and Research
|
|
rejection_reason: Google place types 'point_of_interest', 'establishment' do not match any of the expected heritage institution
|
|
types (museum, library, archive, gallery). The name is also different, and the website (dzs.cz) indicates an educational
|
|
agency, not a heritage institution.
|
|
timestamp: '2025-12-08T19:48:51.117072+00:00'
|
|
youtube_status: NOT_FOUND
|
|
youtube_search_query: Zahraniční instituce official
|
|
youtube_search_timestamp: '2025-12-08T19:48:51.455255+00:00'
|