2137c522db
- 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%
175 lines
6.4 KiB
YAML
175 lines
6.4 KiB
YAML
original_entry:
|
|
name: Akademie věd ČR - Pedagogický ústav J.A.Komenského
|
|
institution_type: LIBRARY
|
|
source: CH-Annotator (czech_unified_ch_annotator.yaml)
|
|
identifiers:
|
|
- &id001
|
|
identifier_scheme: Sigla
|
|
identifier_value: ABB011
|
|
locations:
|
|
- street_address: Máchova 7
|
|
postal_code: 120 00
|
|
city: Praha 2
|
|
country: CZ
|
|
processing_timestamp: '2025-12-06T23:37:23.639904+00:00'
|
|
ghcid:
|
|
ghcid_current: CZ-10-PRA-L-AVCPUJK
|
|
ghcid_original: CZ-XX-PRA-L-AVČPÚJK
|
|
ghcid_uuid: 6c0c0023-d809-5af7-9792-3a88280b05cc
|
|
ghcid_uuid_sha256: c7d810dd-72ec-871c-87f0-147e22c4f1b9
|
|
ghcid_numeric: 14400278351819056924
|
|
record_id: b51bbf12-d5c6-492c-9a1a-f19d1d6b61e7
|
|
generation_timestamp: '2025-12-06T23:37:23.639904+00:00'
|
|
location_resolution:
|
|
country_code: CZ
|
|
region_code: '10'
|
|
city_code: PRA
|
|
method: GEONAMES_CITY_LOOKUP
|
|
region_name: CZ-10
|
|
geonames_id: 8629195
|
|
resolution_timestamp: '2025-12-07T11:42:54.224540+00:00'
|
|
ghcid_history:
|
|
- ghcid: CZ-10-PRA-L-AVCPUJK
|
|
ghcid_numeric: 14400278351819056924
|
|
valid_from: '2025-12-08T11:21:29.200637+00:00'
|
|
reason: 'Normalized diacritics to ASCII per ABBREV-DIACRITICS rule (was: CZ-10-PRA-L-AVČPÚJK)'
|
|
- ghcid: CZ-XX-PRA-L-AVČPÚJK
|
|
ghcid_numeric: 11911444671767460800
|
|
valid_from: '2025-12-06T23:37:23.639904+00:00'
|
|
reason: Initial GHCID from CH-Annotator (czech_unified_ch_annotator.yaml)
|
|
valid_to: '2025-12-08T11:21:29.200637+00:00'
|
|
- ghcid: CZ-10-PRA-L-AVČPÚJK
|
|
valid_from: '2025-12-07T11:42:54.224551+00:00'
|
|
reason: 'Region resolved via GeoNames city lookup: XX->10 (Praha Klanovice)'
|
|
custodian_name:
|
|
claim_type: custodian_name
|
|
claim_value: Akademie věd ČR - Pedagogický ústav J.A.Komenského
|
|
source_type: ch_annotator
|
|
identifiers:
|
|
- identifier_scheme: GHCID
|
|
identifier_value: CZ-10-PRA-L-AVCPUJK
|
|
- identifier_scheme: GHCID_UUID
|
|
identifier_value: 6c0c0023-d809-5af7-9792-3a88280b05cc
|
|
- identifier_scheme: GHCID_UUID_SHA256
|
|
identifier_value: c7d810dd-72ec-871c-87f0-147e22c4f1b9
|
|
- identifier_scheme: GHCID_NUMERIC
|
|
identifier_value: '14400278351819056924'
|
|
- identifier_scheme: RECORD_ID
|
|
identifier_value: b51bbf12-d5c6-492c-9a1a-f19d1d6b61e7
|
|
- *id001
|
|
provenance:
|
|
data_source: API_SCRAPING
|
|
data_tier: TIER_1_AUTHORITATIVE
|
|
extraction_date: '2025-11-19T10:14:30.030561+00:00'
|
|
extraction_method: 'Created from CH-Annotator file: czech_unified_ch_annotator.yaml'
|
|
confidence_score: 0.95
|
|
notes:
|
|
- 'YouTube/Google Maps enrichment 2025-12-08T19:49:41Z: 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.LIB
|
|
subtype_label: LIBRARY
|
|
ontology_class: schema:Library
|
|
alternative_classes:
|
|
- org:FormalOrganization
|
|
- rov:RegisteredOrganization
|
|
- glam:HeritageCustodian
|
|
extraction_provenance:
|
|
namespace: glam
|
|
path: /files/czech_unified.yaml
|
|
timestamp: '2025-11-19T10:14:30.030561+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: 0.95
|
|
verified: false
|
|
verification_date:
|
|
verified_by:
|
|
entity_claims:
|
|
- claim_type: full_name
|
|
claim_value: Akademie věd ČR - Pedagogický ústav J.A.Komenského
|
|
property_uri: skos:prefLabel
|
|
provenance:
|
|
namespace: glam
|
|
path: /files/czech_unified.yaml
|
|
timestamp: '2025-11-19T10:14:30.030561+00:00'
|
|
agent: claude-conversation
|
|
context_convention: ch_annotator-v1_7_0
|
|
confidence: 0.95
|
|
- claim_type: institution_type
|
|
claim_value: LIBRARY
|
|
property_uri: rdf:type
|
|
provenance:
|
|
namespace: glam
|
|
path: /files/czech_unified.yaml
|
|
timestamp: '2025-11-19T10:14:30.030561+00:00'
|
|
agent: claude-conversation
|
|
context_convention: ch_annotator-v1_7_0
|
|
confidence: 0.95
|
|
- claim_type: located_in_city
|
|
claim_value: Praha 2
|
|
property_uri: schema:addressLocality
|
|
provenance:
|
|
namespace: glam
|
|
path: /files/czech_unified.yaml
|
|
timestamp: '2025-11-19T10:14:30.030561+00:00'
|
|
agent: claude-conversation
|
|
context_convention: ch_annotator-v1_7_0
|
|
confidence: 0.9
|
|
- claim_type: ghcid
|
|
claim_value: CZ-ABB011
|
|
property_uri: glam:ghcid
|
|
provenance:
|
|
namespace: glam
|
|
path: /files/czech_unified.yaml
|
|
timestamp: '2025-11-19T10:14:30.030561+00:00'
|
|
agent: claude-conversation
|
|
context_convention: ch_annotator-v1_7_0
|
|
confidence: 1.0
|
|
integration_note:
|
|
created_from: czech_unified_ch_annotator.yaml
|
|
creation_date: '2025-12-06T23:37:23.639904+00:00'
|
|
creation_method: create_custodian_from_ch_annotator.py
|
|
google_maps_status: NO_MATCH
|
|
google_maps_rejected:
|
|
candidate_name: Czech Academy of Sciences
|
|
rejection_reason: This is a mismatch. The source is a specific research institute within the Czech Academy of Sciences.
|
|
The Google Maps candidate represents the overarching parent organization, the Czech Academy of Sciences, located at its
|
|
headquarters. The candidate's Google Place types ('point_of_interest', 'establishment') are generic and do not match the
|
|
expected types for a heritage institution. Furthermore, the website links to the main academy, not the specific Pedagogical
|
|
Institute.
|
|
timestamp: '2025-12-08T19:49:41.002827+00:00'
|
|
youtube_status: NOT_FOUND
|
|
youtube_search_query: Akademie věd ČR - Pedagogický ústav J.A.Komenského official
|
|
youtube_search_timestamp: '2025-12-08T19:49:41.371035+00:00'
|
|
location:
|
|
city: Prague
|
|
region: CZ-10
|
|
region_code: '10'
|
|
country: CZ
|
|
postal_code: 120 00
|
|
street_address: Máchova 7
|
|
geonames_id: 3067696
|
|
normalization_timestamp: '2025-12-09T20:40:58.718568+00:00'
|
|
latitude: 50.08804
|
|
longitude: 14.42076
|
|
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: '2025-12-09T20:40:58.718556+00:00'
|