85a951bbea
- Fixed 469 JP files missing location: blocks (had data in original_entry.locations)
- Fixed 117 additional JP files found in second pass
- 1 EG file skipped (no location source data available)
- Total files with location: blocks now 27,459 out of 27,511 (99.8%)
- Also includes YAML formatting standardization (line wrapping)
Recovery from data loss in commit 62fdd35321 is now complete.
211 lines
6.8 KiB
YAML
211 lines
6.8 KiB
YAML
original_entry:
|
|
name: Státní oblastní archiv v Litoměřicích - Státní okresní archiv Děčín
|
|
institution_type: OFFICIAL_INSTITUTION
|
|
source: CH-Annotator (czech_unified_ch_annotator.yaml)
|
|
identifiers:
|
|
- &id001
|
|
identifier_scheme: Sigla
|
|
identifier_value: DCE001
|
|
- &id002
|
|
identifier_scheme: IČO
|
|
identifier_value: '70979464'
|
|
- &id003
|
|
identifier_scheme: DIČ
|
|
identifier_value: CZ70979464
|
|
- &id004
|
|
identifier_scheme: Website
|
|
identifier_value: https://www.soalitomerice.cz/soka-decin/
|
|
identifier_url: https://www.soalitomerice.cz/soka-decin/
|
|
- &id005
|
|
identifier_scheme: Wikidata
|
|
identifier_value: Q114618026
|
|
identifier_url: https://www.wikidata.org/wiki/Q114618026
|
|
locations:
|
|
- street_address: Dlouhá jízda 1253 - Zámek
|
|
postal_code: 405 01
|
|
city: Děčín
|
|
region: Ústecký
|
|
country: CZ
|
|
latitude: 50.778892
|
|
longitude: 14.209606
|
|
processing_timestamp: '2025-12-06T23:37:17.466837+00:00'
|
|
ghcid:
|
|
ghcid_current: CZ-US-DEC-O-SOAVLSOAD
|
|
ghcid_original: CZ-US-DEC-O-SOAVLSOAD
|
|
ghcid_uuid: 2f761e22-6abc-5432-bc4c-18973431273e
|
|
ghcid_uuid_sha256: 682d0038-f421-8115-c68f-51c74d09812f
|
|
ghcid_numeric: 7506656398510481685
|
|
record_id: e68fc23e-2c88-474a-a012-192cf0039c94
|
|
generation_timestamp: '2025-12-06T23:37:17.466837+00:00'
|
|
location_resolution:
|
|
country_code: CZ
|
|
region_code: US
|
|
city_code: DEC
|
|
method: CH_ANNOTATOR_SOURCE
|
|
ghcid_history:
|
|
- ghcid: CZ-US-DEC-O-SOAVLSOAD
|
|
ghcid_numeric: 7506656398510481685
|
|
valid_from: '2025-12-06T23:37:17.466837+00:00'
|
|
reason: Initial GHCID from CH-Annotator (czech_unified_ch_annotator.yaml)
|
|
custodian_name:
|
|
claim_type: custodian_name
|
|
claim_value: Státní oblastní archiv v Litoměřicích - Státní okresní archiv Děčín
|
|
source_type: ch_annotator
|
|
identifiers:
|
|
- identifier_scheme: GHCID
|
|
identifier_value: CZ-US-DEC-O-SOAVLSOAD
|
|
- identifier_scheme: GHCID_UUID
|
|
identifier_value: 2f761e22-6abc-5432-bc4c-18973431273e
|
|
- identifier_scheme: GHCID_UUID_SHA256
|
|
identifier_value: 682d0038-f421-8115-c68f-51c74d09812f
|
|
- identifier_scheme: GHCID_NUMERIC
|
|
identifier_value: '7506656398510481685'
|
|
- identifier_scheme: RECORD_ID
|
|
identifier_value: e68fc23e-2c88-474a-a012-192cf0039c94
|
|
- *id001
|
|
- *id002
|
|
- *id003
|
|
- *id004
|
|
- *id005
|
|
provenance:
|
|
data_source: API_SCRAPING
|
|
data_tier: TIER_1_AUTHORITATIVE
|
|
extraction_date: '2025-11-19T10:14:29.936540+00:00'
|
|
extraction_method: 'Created from CH-Annotator file: czech_unified_ch_annotator.yaml'
|
|
confidence_score: 0.95
|
|
ch_annotator:
|
|
convention_id: ch_annotator-v1_7_0
|
|
convention_version: 1.7.0
|
|
entity_classification:
|
|
hypernym: GRP
|
|
hypernym_label: GROUP
|
|
subtype: GRP.HER.OFF
|
|
subtype_label: OFFICIAL_INSTITUTION
|
|
ontology_class: schema:GovernmentOrganization
|
|
alternative_classes:
|
|
- org:FormalOrganization
|
|
- rov:RegisteredOrganization
|
|
- glam:HeritageCustodian
|
|
extraction_provenance:
|
|
namespace: glam
|
|
path: /files/czech_unified.yaml
|
|
timestamp: '2025-11-19T10:14:29.936540+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: null
|
|
verified_by: null
|
|
entity_claims:
|
|
- claim_type: full_name
|
|
claim_value: Státní oblastní archiv v Litoměřicích - Státní okresní archiv Děčín
|
|
property_uri: skos:prefLabel
|
|
provenance:
|
|
namespace: glam
|
|
path: /files/czech_unified.yaml
|
|
timestamp: '2025-11-19T10:14:29.936540+00:00'
|
|
agent: claude-conversation
|
|
context_convention: ch_annotator-v1_7_0
|
|
confidence: 0.95
|
|
- claim_type: institution_type
|
|
claim_value: OFFICIAL_INSTITUTION
|
|
property_uri: rdf:type
|
|
provenance:
|
|
namespace: glam
|
|
path: /files/czech_unified.yaml
|
|
timestamp: '2025-11-19T10:14:29.936540+00:00'
|
|
agent: claude-conversation
|
|
context_convention: ch_annotator-v1_7_0
|
|
confidence: 0.95
|
|
- claim_type: located_in_city
|
|
claim_value: Děčín
|
|
property_uri: schema:addressLocality
|
|
provenance:
|
|
namespace: glam
|
|
path: /files/czech_unified.yaml
|
|
timestamp: '2025-11-19T10:14:29.936540+00:00'
|
|
agent: claude-conversation
|
|
context_convention: ch_annotator-v1_7_0
|
|
confidence: 0.9
|
|
- claim_type: wikidata_id
|
|
claim_value: Q114618026
|
|
property_uri: owl:sameAs
|
|
provenance:
|
|
namespace: wikidata
|
|
path: /entity/Q114618026
|
|
timestamp: '2025-11-19T10:14:29.936540+00:00'
|
|
agent: claude-conversation
|
|
context_convention: ch_annotator-v1_7_0
|
|
confidence: 0.98
|
|
- claim_type: ghcid
|
|
claim_value: CZ-DCE001
|
|
property_uri: glam:ghcid
|
|
provenance:
|
|
namespace: glam
|
|
path: /files/czech_unified.yaml
|
|
timestamp: '2025-11-19T10:14:29.936540+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: '2025-12-06T23:37:17.466837+00:00'
|
|
creation_method: create_custodian_from_ch_annotator.py
|
|
wikidata_enrichment:
|
|
wikidata_entity_id: Q114618026
|
|
api_metadata:
|
|
api_endpoint: https://www.wikidata.org/w/rest.php/wikibase/v1
|
|
fetch_timestamp: '2025-12-09T09:37:46.000050+00:00'
|
|
user_agent: GLAMDataExtractor/1.1 (glam-data@example.com) Python/httpx
|
|
enrichment_version: 2.0_full
|
|
properties_found:
|
|
- P31
|
|
- P17
|
|
- P159
|
|
- P968
|
|
wikidata_labels:
|
|
cs: Státní oblastní archiv v Litoměřicích, Státní okresní archiv Děčín, knihovna
|
|
en: State Regional Archives Litomerice, State District Archives Decin
|
|
wikidata_label_en: State Regional Archives Litomerice, State District Archives Decin
|
|
wikidata_descriptions:
|
|
cs: knihovna v obci Děčín v okrese Děčín
|
|
wikidata_aliases:
|
|
cs:
|
|
- SOkA Děčín
|
|
wikidata_classification:
|
|
instance_of: &id006
|
|
- id: Q25504402
|
|
label: archival library
|
|
description: library of an archive
|
|
wikidata_instance_of: *id006
|
|
wikidata_location:
|
|
country: &id007
|
|
id: Q213
|
|
label: Czech Republic
|
|
description: country in Central Europe
|
|
headquarters_location:
|
|
id: Q146307
|
|
label: Děčín
|
|
description: town in Ústí nad Labem Region, Czechia
|
|
wikidata_country: *id007
|
|
wikidata_contact:
|
|
email: mailto:votapek@soalitomerice.cz
|
|
location:
|
|
latitude: 50.778892
|
|
longitude: 14.209606
|
|
coordinate_provenance:
|
|
source_type: ORIGINAL_ENTRY
|
|
source_path: original_entry.locations[0]
|
|
city: Děčín
|
|
region: Ústecký
|
|
region_code: US
|
|
country: *id007
|
|
postal_code: 405 01
|
|
street_address: Dlouhá jízda 1253 - Zámek
|
|
normalization_timestamp: '2025-12-09T10:54:14.944449+00:00'
|