glam/data/custodian/CZ-42-LOU-A-SOAL.yaml
2025-12-30 23:01:01 +01:00

316 lines
11 KiB
YAML

custodian_name:
claim_type: custodian_name
claim_value: Státní okresní archiv Louny
source_type: ch_annotator
original_entry:
name: Státní okresní archiv Louny
institution_type: ARCHIVE
source: CH-Annotator (czech_unified_ch_annotator.yaml)
identifiers:
- &id001
identifier_scheme: ARON_UUID
identifier_value: 11a015d2-eb5b-4b4d-8711-2d5c75eb1ee0
identifier_url: https://portal.nacr.cz/aron/apu/11a015d2-eb5b-4b4d-8711-2d5c75eb1ee0
- &id002
identifier_scheme: INSTITUTION_CODE
identifier_value: '224104010'
- &id003
identifier_scheme: Wikidata
identifier_value: Q53200605
identifier_url: https://www.wikidata.org/wiki/Q53200605
- &id004
identifier_scheme: VIAF
identifier_value: '142368962'
identifier_url: https://viaf.org/viaf/142368962
locations: []
processing_timestamp: '2025-12-06T23:37:43.821842+00:00'
ghcid:
ghcid_current: CZ-42-LOU-A-SOAL
ghcid_original: XX-XX-XXX-A-SOAL
ghcid_uuid: ca97979e-c080-5dc0-ad1b-be56c8df613c
ghcid_uuid_sha256: cf0b0c7e-6b71-8877-8bf8-b1d7f26291ae
ghcid_numeric: 14919031927702915191
record_id: 060d428e-af77-465a-9695-6fe95fa1f26d
generation_timestamp: '2025-12-06T23:37:43.821842+00:00'
location_resolution:
country_code: CZ
region_code: '42'
city_code: LOU
method: CH_ANNOTATOR_TOP_SET
resolution_timestamp: '2025-12-07T00:20:05.576857+00:00'
region_name: CZ-42
iso_code_source: CZ-42
city_name: Louny
geonames_id: 3071507
feature_code: PPL
extracted_toponym: Louny
latitude: 50.35699
longitude: 13.79667
ghcid_history:
- ghcid: XX-XX-XXX-A-SOAL
ghcid_numeric: 14919031927702915191
valid_from: '2025-12-06T23:37:43.821842+00:00'
reason: Initial GHCID from CH-Annotator (czech_unified_ch_annotator.yaml)
- ghcid: CZ-XX-XXX-A-SOAL
valid_from: '2025-12-06T23:54:40.212784+00:00'
reason: 'Country resolved via Wikidata P17: XX→CZ'
- ghcid: CZ-42-XXX-A-SOAL
valid_from: '2025-12-07T00:01:31.836000+00:00'
reason: 'Region resolved via Wikidata P131: XX->42 (CZ-42)'
- ghcid: CZ-42-LOU-A-SOAL
valid_from: '2025-12-07T00:20:05.576866+00:00'
reason: 'Location resolved via CH-Annotator TOP.SET extraction: Louny -> Louny (GeoNames:3071507)'
identifiers:
- identifier_scheme: GHCID
identifier_value: XX-XX-XXX-A-SOAL
- identifier_scheme: GHCID_UUID
identifier_value: ca97979e-c080-5dc0-ad1b-be56c8df613c
- identifier_scheme: GHCID_UUID_SHA256
identifier_value: cf0b0c7e-6b71-8877-8bf8-b1d7f26291ae
- identifier_scheme: GHCID_NUMERIC
identifier_value: '14919031927702915191'
- identifier_scheme: RECORD_ID
identifier_value: 060d428e-af77-465a-9695-6fe95fa1f26d
- *id001
- *id002
- *id003
- *id004
provenance:
data_source: API_SCRAPING
data_tier: TIER_1_AUTHORITATIVE
extraction_date: '2025-11-19T11:35:45.743445+00:00'
extraction_method: 'Created from CH-Annotator file: czech_unified_ch_annotator.yaml'
confidence_score: 0.85
notes:
- 'Country resolved 2025-12-06T23:54:40Z: XX→CZ via Wikidata P17'
- 'Region resolved 2025-12-07T00:01:31Z: XX->42 via Wikidata P131 (CZ-42)'
- 'Location resolved 2025-12-07T00:20:05Z: CH-Annotator TOP.SET extraction ''Louny'' -> Louny (GeoNames:3071507, Region:80)'
- Canonical location added via normalize_custodian_files.py on 2025-12-08T23:48:12Z
- Canonical location added via normalize_custodian_files.py on 2025-12-09T06:49:35Z
- 'YouTube/Google Maps enrichment 2025-12-09T09:31:23Z: YouTube: not found'
schema_version: 2.0.0
enrichment_provenance:
wikidata_enrichment:
content_hash: sha256-pKAhF6+6y/KNeiYdDb10BqUjW+vkOJfdyZ6H+s9kUeI=
verified_at: '2025-12-28T19:59:03.474508+00:00'
wasDerivedFrom: https://www.wikidata.org/wiki/Q53200605
provenance_schema_version: '2.0'
standards_compliance:
- W3C PROV-O
- W3C SRI (content hashes)
generated_at: '2025-12-28T19:59:03.474527+00:00'
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: '2025-11-19T11:35:45.743445+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: Státní okresní archiv Louny
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: '2025-11-19T11:35:45.743445+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: '2025-11-19T11:35:45.743445+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: wikidata_id
claim_value: Q53200605
property_uri: owl:sameAs
provenance:
namespace: wikidata
path: /entity/Q53200605
agent: batch-script-create-custodian-from-ch-annotator
context_convention: ch_annotator-v1_7_0
source_archived_at: '2025-11-19T11:35:45.743445+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: 0.98
- claim_type: location_settlement
claim_value: Louny
property_uri: schema:location
hypernym_code: TOP.SET
hypernym_label: SETTLEMENT
provenance:
namespace: geonames
path: /geonames/3071507
timestamp: '2025-12-07T00:20:05.576869+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: Louny
method: pattern_matching
integration_note:
created_from: czech_unified_ch_annotator.yaml
creation_date: '2025-12-06T23:37:43.821842+00:00'
creation_method: create_custodian_from_ch_annotator.py
wikidata_enrichment:
wikidata_entity_id: Q53200605
api_metadata:
api_endpoint: https://www.wikidata.org/w/rest.php/wikibase/v1
fetch_timestamp: '2025-12-08T23:43:45.303724+00:00'
user_agent: GLAMDataExtractor/1.1 (glam-data@example.com) Python/httpx
enrichment_version: 2.0_full
properties_found:
- P31
- P17
- P214
- P856
- P18
- P159
- P361
- P131
- P373
wikidata_labels:
cs: Státní okresní archiv Louny
en: State District Archives Louny
wikidata_label_en: State District Archives Louny
wikidata_descriptions:
cs: archiv v Lounech
en: archive in Louny
wikidata_description_en: archive in Louny
wikidata_aliases:
cs:
- SOkA Louny
wikidata_sitelinks:
cswiki: Státní okresní archiv Louny
commonswiki: Category:Státní okresní archiv Louny
wikidata_classification:
instance_of: &id005
- id: Q53131316
label: state district archive
description: Archive type in the Czech Republic
wikidata_instance_of: *id005
wikidata_location:
country: &id006
id: Q213
label: Czech Republic
description: country in Central Europe
headquarters_location:
id: Q31741267
label: Daliborka house in Louny
description: house in Louny, Czech Republic
located_in_admin_entity: &id007
id: Q616877
label: Louny
description: town in Czechia
wikidata_country: *id006
wikidata_located_in: *id007
wikidata_organization:
part_of:
id: Q18920590
label: State Regional Archives Litoměřice
description: regional archive
wikidata_web:
official_website: http://www.soalitomerice.cz/soka-louny/
wikidata_official_website: http://www.soalitomerice.cz/soka-louny/
wikidata_media:
image: Louny, renesanční dům čp.57.JPG
commons_category: Státní okresní archiv Louny
wikidata_image: Louny, renesanční dům čp.57.JPG
_provenance:
content_hash:
algorithm: sha256
value: sha256-pKAhF6+6y/KNeiYdDb10BqUjW+vkOJfdyZ6H+s9kUeI=
scope: enrichment_section
computed_at: '2025-12-28T19:59:03.474508+00:00'
prov:
wasGeneratedBy:
'@type': prov:Activity
name: wikidata_api_fetch
used: https://www.wikidata.org/w/rest.php/wikibase/v1
wasDerivedFrom: https://www.wikidata.org/wiki/Q53200605
verification:
status: verified
last_verified: '2025-12-28T19:59:03.474517+00:00'
location:
latitude: 50.35699
longitude: 13.79667
coordinate_provenance:
source_type: GHCID_RESOLUTION_DIRECT
source_path: ghcid.location_resolution
original_timestamp: '2025-12-07T00:20:05.576857+00:00'
entity_id: 3071507
resolution_method: CH_ANNOTATOR_TOP_SET
city: Louny
region: CZ-42
region_code: '42'
country: CZ
geonames_id: 3071507
feature_code: PPL
normalization_timestamp: '2025-12-09T06:49:35.688716+00:00'
youtube_status: NOT_FOUND
youtube_search_query: Státní okresní archiv Louny official
youtube_search_timestamp: '2025-12-09T09:31:23.724882+00:00'
logo_enrichment:
enrichment_timestamp: '2025-12-24T13:21:01.486418+00:00'
source_url: http://www.soalitomerice.cz/soka-louny
extraction_method: crawl4ai
claims:
- claim_type: favicon_url
claim_value: https://www.soalitomerice.cz/wp-content/uploads/2024/05/cropped-soa-logo-only-graphics-180x180.png
source_url: http://www.soalitomerice.cz/soka-louny
css_selector: '[document] > html.td-md-is-chrome > body.post-template-default.single > link:nth-of-type(3)'
retrieved_on: '2025-12-24T13:21:01.486418+00:00'
extraction_method: crawl4ai_link_rel
favicon_type: ''
favicon_sizes: ''
- claim_type: og_image_url
claim_value: http://www.soalitomerice.cz/wp-content/uploads/2015/12/IMG_0545-300x200.jpg
source_url: http://www.soalitomerice.cz/soka-louny
css_selector: '[document] > html.td-md-is-chrome > head > meta:nth-of-type(14)'
retrieved_on: '2025-12-24T13:21:01.486418+00:00'
extraction_method: crawl4ai_meta_og
summary:
total_claims: 2
has_primary_logo: false
has_favicon: true
has_og_image: true
favicon_count: 4