- JP: Handle Gun/Cho/Machi/Mura compound city names (2615 files) - CZ: Map city codes to GeoNames entries (667 files) - Overall coverage: 84.5% → 96.4%
154 lines
5.9 KiB
YAML
154 lines
5.9 KiB
YAML
original_entry:
|
|
name: Etnologický ústav AV ČR, v. v. i.
|
|
institution_type: ARCHIVE
|
|
source: CH-Annotator (czech_unified_ch_annotator.yaml)
|
|
identifiers:
|
|
- &id001
|
|
identifier_scheme: ARON_UUID
|
|
identifier_value: 61109c40-868d-491c-a39d-140555d3f52b
|
|
identifier_url: https://portal.nacr.cz/aron/apu/61109c40-868d-491c-a39d-140555d3f52b
|
|
- &id002
|
|
identifier_scheme: INSTITUTION_CODE
|
|
identifier_value: '901100270'
|
|
locations: []
|
|
processing_timestamp: '2025-12-06T23:37:44.204681+00:00'
|
|
ghcid:
|
|
ghcid_current: CZ-10-PRA-A-EUACVV
|
|
ghcid_original: XX-XX-XXX-A-EÚAČVV
|
|
ghcid_uuid: fae72abb-3eea-5d4d-bad8-dbe3abb8014f
|
|
ghcid_uuid_sha256: 99daa3fd-54ec-864b-be8e-1c4375b5a2df
|
|
ghcid_numeric: 11086353741172766283
|
|
record_id: 58ce77ea-6e15-4300-a84a-b5b3aa6f926b
|
|
generation_timestamp: '2025-12-06T23:37:44.204681+00:00'
|
|
location_resolution:
|
|
country_code: CZ
|
|
region_code: 10
|
|
city_code: PRA
|
|
method: NAME_PATTERN_EXTRACTION
|
|
resolution_timestamp: '2025-12-06T23:56:12.211112+00:00'
|
|
resolution_notes: City 'AV ČR' extracted from institution name
|
|
ghcid_history:
|
|
- ghcid: CZ-10-PRA-A-EUACVV
|
|
ghcid_numeric: 11086353741172766283
|
|
valid_from: '2025-12-08T11:21:36.751243+00:00'
|
|
reason: 'Normalized diacritics to ASCII per ABBREV-DIACRITICS rule (was: CZ-10-PRA-A-EÚAČVV)'
|
|
- ghcid: XX-XX-XXX-A-EÚAČVV
|
|
ghcid_numeric: 16847279402465468603
|
|
valid_from: '2025-12-06T23:37:44.204681+00:00'
|
|
reason: Initial GHCID from CH-Annotator (czech_unified_ch_annotator.yaml)
|
|
valid_to: '2025-12-08T11:21:36.751243+00:00'
|
|
- ghcid: CZ-XX-XXX-A-EÚAČVV
|
|
valid_from: '2025-12-06T23:56:12.211122+00:00'
|
|
reason: 'Country resolved via Wikidata P17: XX→CZ'
|
|
- ghcid: CZ-10-PRA-A-EÚAČVV
|
|
valid_from: '2025-12-07T12:38:22.565290+00:00'
|
|
reason: 'Location resolved from institution name pattern: ''AV ČR'' → region 10, city PRA'
|
|
custodian_name:
|
|
claim_type: custodian_name
|
|
claim_value: Etnologický ústav AV ČR, v. v. i.
|
|
source_type: ch_annotator
|
|
identifiers:
|
|
- identifier_scheme: GHCID
|
|
identifier_value: CZ-10-PRA-A-EUACVV
|
|
- identifier_scheme: GHCID_UUID
|
|
identifier_value: fae72abb-3eea-5d4d-bad8-dbe3abb8014f
|
|
- identifier_scheme: GHCID_UUID_SHA256
|
|
identifier_value: 99daa3fd-54ec-864b-be8e-1c4375b5a2df
|
|
- identifier_scheme: GHCID_NUMERIC
|
|
identifier_value: '11086353741172766283'
|
|
- identifier_scheme: RECORD_ID
|
|
identifier_value: 58ce77ea-6e15-4300-a84a-b5b3aa6f926b
|
|
- *id001
|
|
- *id002
|
|
provenance:
|
|
data_source: API_SCRAPING
|
|
data_tier: TIER_1_AUTHORITATIVE
|
|
extraction_date: '2025-11-19T11:35:45.744242+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'
|
|
- 'YouTube/Google Maps enrichment 2025-12-08T19:47:19Z: 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 2025-12-08T23:48:04Z
|
|
- Canonical location added via normalize_custodian_files.py on 2025-12-09T06:49:28Z
|
|
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: '2025-11-19T11:35:45.744242+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:
|
|
verified_by:
|
|
entity_claims:
|
|
- claim_type: full_name
|
|
claim_value: Etnologický ústav AV ČR, v. v. i.
|
|
property_uri: skos:prefLabel
|
|
provenance:
|
|
namespace: glam
|
|
path: /files/czech_unified.yaml
|
|
timestamp: '2025-11-19T11:35:45.744242+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: '2025-11-19T11:35:45.744242+00:00'
|
|
agent: claude-conversation
|
|
context_convention: ch_annotator-v1_7_0
|
|
confidence: 0.95
|
|
integration_note:
|
|
created_from: czech_unified_ch_annotator.yaml
|
|
creation_date: '2025-12-06T23:37:44.204681+00:00'
|
|
creation_method: create_custodian_from_ch_annotator.py
|
|
google_maps_status: NO_MATCH
|
|
google_maps_rejected:
|
|
candidate_name: Etnologický Ústav Av ČR V.v.i.
|
|
rejection_reason: Reject due to TYPE MATCH failure. The name and location are a clear match, but the Google Place types
|
|
'point_of_interest', 'establishment' are too generic and do not indicate a heritage institution like a museum, library,
|
|
or archive. A higher-confidence match requires more specific Google Place types.
|
|
timestamp: '2025-12-08T19:47:19.373261+00:00'
|
|
youtube_status: NOT_FOUND
|
|
youtube_search_query: Etnologický ústav AV ČR, v. v. i. official
|
|
youtube_search_timestamp: '2025-12-08T19:47:19.718210+00:00'
|
|
location:
|
|
region_code: 10
|
|
country: CZ
|
|
normalization_timestamp: '2025-12-09T20:40:58.045487+00:00'
|
|
latitude: 50.08804
|
|
longitude: 14.42076
|
|
city: Prague
|
|
geonames_id: 3067696
|
|
geonames_name: Prague
|
|
feature_code: PPLC
|
|
coordinate_provenance:
|
|
source_type: GEONAMES_GHCID_CITY_CODE
|
|
source_path: data/reference/geonames.db
|
|
entity_id: 3067696
|
|
city_code: PRA
|
|
original_timestamp: '2025-12-09T20:40:58.045460+00:00'
|