glam/data/custodian/CZ-32-ROK-A-SOAR-statni_okresni_archiv_rokycany.yaml
2025-12-30 23:01:01 +01:00

317 lines
11 KiB
YAML

original_entry:
name: Státní okresní archiv Rokycany
institution_type: ARCHIVE
source: CH-Annotator (czech_unified_ch_annotator.yaml)
identifiers:
- &id001
identifier_scheme: ARON_UUID
identifier_value: 4dcfaf53-8677-4c81-8c85-3bab8f67cf8e
identifier_url: https://portal.nacr.cz/aron/apu/4dcfaf53-8677-4c81-8c85-3bab8f67cf8e
- &id002
identifier_scheme: INSTITUTION_CODE
identifier_value: '223106010'
- &id003
identifier_scheme: Wikidata
identifier_value: Q54017304
identifier_url: https://www.wikidata.org/wiki/Q54017304
- &id004
identifier_scheme: VIAF
identifier_value: '236563247'
identifier_url: https://viaf.org/viaf/236563247
locations: []
processing_timestamp: '2025-12-06T23:37:44.111276+00:00'
ghcid:
ghcid_current: CZ-32-ROK-A-SOAR-statni_okresni_archiv_rokycany
ghcid_original: XX-XX-XXX-A-SOAR-statni_okresni_archiv_rokycany
ghcid_uuid: 201645a7-504e-5692-8824-ac5b0d699223
ghcid_uuid_sha256: 2305c386-6987-8dab-a4be-bda457bb362b
ghcid_numeric: 2523638148274572715
record_id: f0d0b87f-5db7-4a8e-b0a4-85670c937d61
generation_timestamp: '2025-12-06T23:37:44.111276+00:00'
location_resolution:
country_code: CZ
region_code: '32'
city_code: ROK
method: CH_ANNOTATOR_TOP_SET
resolution_timestamp: '2025-12-07T00:20:05.329065+00:00'
region_name: CZ-32
iso_code_source: CZ-32
city_name: Rokycany
geonames_id: 3066794
feature_code: PPL
extracted_toponym: Rokycany
latitude: 49.7427
longitude: 13.59459
ghcid_history:
- ghcid: XX-XX-XXX-A-SOAR-statni_okresni_archiv_rokycany
ghcid_numeric: 2523638148274572715
valid_from: '2025-12-06T23:37:44.111276+00:00'
reason: Initial GHCID from CH-Annotator (czech_unified_ch_annotator.yaml)
- ghcid: CZ-XX-XXX-A-SOAR-statni_okresni_archiv_rokycany
valid_from: '2025-12-06T23:54:40.183126+00:00'
reason: 'Country resolved via Wikidata P17: XX→CZ'
- ghcid: CZ-32-XXX-A-SOAR-statni_okresni_archiv_rokycany
valid_from: '2025-12-06T23:59:58.886940+00:00'
reason: 'Region resolved via Wikidata P131: XX->32 (CZ-32)'
- ghcid: CZ-32-ROK-A-SOAR-statni_okresni_archiv_rokycany
valid_from: '2025-12-07T00:20:05.329075+00:00'
reason: 'Location resolved via CH-Annotator TOP.SET extraction: Rokycany -> Rokycany (GeoNames:3066794)'
custodian_name:
claim_type: custodian_name
claim_value: Státní okresní archiv Rokycany
source_type: ch_annotator
identifiers:
- identifier_scheme: GHCID
identifier_value: XX-XX-XXX-A-SOAR-statni_okresni_archiv_rokycany
- identifier_scheme: GHCID_UUID
identifier_value: 201645a7-504e-5692-8824-ac5b0d699223
- identifier_scheme: GHCID_UUID_SHA256
identifier_value: 2305c386-6987-8dab-a4be-bda457bb362b
- identifier_scheme: GHCID_NUMERIC
identifier_value: '2523638148274572715'
- identifier_scheme: RECORD_ID
identifier_value: f0d0b87f-5db7-4a8e-b0a4-85670c937d61
- *id001
- *id002
- *id003
- *id004
provenance:
data_source: API_SCRAPING
data_tier: TIER_1_AUTHORITATIVE
extraction_date: '2025-11-19T11:35:45.744056+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 2025-12-06T23:59:58Z: XX->32 via Wikidata P131 (CZ-32)'
- 'Location resolved 2025-12-07T00:20:05Z: CH-Annotator TOP.SET extraction ''Rokycany'' -> Rokycany (GeoNames:3066794, Region:71)'
- Canonical location added via normalize_custodian_files.py on 2025-12-08T23:48:11Z
- Canonical location added via normalize_custodian_files.py on 2025-12-09T06:49:34Z
- 'YouTube/Google Maps enrichment 2025-12-09T09:30:57Z: YouTube: not found'
schema_version: 2.0.0
enrichment_provenance:
wikidata_enrichment:
content_hash: sha256-DmQe3382Bw6fFm/bQ8o2KHhbxkkrdmZRz90LkJyu1jw=
verified_at: '2025-12-28T19:58:56.555425+00:00'
wasDerivedFrom: https://www.wikidata.org/wiki/Q54017304
provenance_schema_version: '2.0'
standards_compliance:
- W3C PROV-O
- W3C SRI (content hashes)
generated_at: '2025-12-28T19:58:56.555440+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: '2025-11-19T11:35:45.744056+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 Rokycany
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: '2025-11-19T11:35:45.744056+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: '2025-11-19T11:35:45.744056+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: Q54017304
property_uri: owl:sameAs
provenance:
namespace: wikidata
path: /entity/Q54017304
agent: batch-script-create-custodian-from-ch-annotator
context_convention: ch_annotator-v1_7_0
source_archived_at: '2025-11-19T11:35:45.744056+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: Rokycany
property_uri: schema:location
hypernym_code: TOP.SET
hypernym_label: SETTLEMENT
provenance:
namespace: geonames
path: /geonames/3066794
timestamp: '2025-12-07T00:20:05.329078+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: Rokycany
method: pattern_matching
integration_note:
created_from: czech_unified_ch_annotator.yaml
creation_date: '2025-12-06T23:37:44.111276+00:00'
creation_method: create_custodian_from_ch_annotator.py
wikidata_enrichment:
wikidata_entity_id: Q54017304
api_metadata:
api_endpoint: https://www.wikidata.org/w/rest.php/wikibase/v1
fetch_timestamp: '2025-12-08T23:43:24.553588+00:00'
user_agent: GLAMDataExtractor/1.1 (glam-data@example.com) Python/httpx
enrichment_version: 2.0_full
properties_found:
- P31
- P17
- P361
- P159
- P214
- P227
- P856
- P18
- P373
- P131
wikidata_labels:
cs: Státní okresní archiv Rokycany
en: Státní okresní archiv Rokycany
fr: Státní okresní archiv Rokycany
wikidata_label_en: Státní okresní archiv Rokycany
wikidata_label_fr: Státní okresní archiv Rokycany
wikidata_descriptions:
cs: archiv v Rokycanech
en: archive in Rokycany
fr: maison d'édition
ar: دار نشر
wikidata_description_en: archive in Rokycany
wikidata_aliases:
cs:
- SOkA Rokycany
en:
- SOkA Rokycany
wikidata_sitelinks:
commonswiki: Category:Státní okresní archiv Rokycany
cswiki: Státní okresní archiv Rokycany
wikidata_classification:
instance_of: &id005
- id: Q53131316
label: state district archive
description: Archive type in the Czech Republic
- id: Q2085381
label: publishing company
description: company that prints and distributes pressed goods or electronic media
wikidata_instance_of: *id005
wikidata_location:
country: &id007
id: Q213
label: Czech Republic
description: country in Central Europe
headquarters_location: &id006
id: Q12045685
label: Plzeňské Předměstí
description: neighborhood of Rokycany
located_in_admin_entity: *id006
wikidata_country: *id007
wikidata_located_in: *id006
wikidata_organization:
part_of:
id: Q21953079
label: State Regional Archives in Pilsen
description: archive covering West Bohemia, Czechia
wikidata_web:
official_website: http://www.soaplzen.cz/soka-ro
wikidata_official_website: http://www.soaplzen.cz/soka-ro
wikidata_media:
image: Státní okresní archiv Rokycany 02.jpg
commons_category: Státní okresní archiv Rokycany
wikidata_image: Státní okresní archiv Rokycany 02.jpg
_provenance:
content_hash:
algorithm: sha256
value: sha256-DmQe3382Bw6fFm/bQ8o2KHhbxkkrdmZRz90LkJyu1jw=
scope: enrichment_section
computed_at: '2025-12-28T19:58:56.555425+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/Q54017304
verification:
status: verified
last_verified: '2025-12-28T19:58:56.555432+00:00'
location:
latitude: 49.7427
longitude: 13.59459
coordinate_provenance:
source_type: GHCID_RESOLUTION_DIRECT
source_path: ghcid.location_resolution
original_timestamp: '2025-12-07T00:20:05.329065+00:00'
entity_id: 3066794
resolution_method: CH_ANNOTATOR_TOP_SET
city: Rokycany
region: CZ-32
region_code: '32'
country: CZ
geonames_id: 3066794
feature_code: PPL
normalization_timestamp: '2025-12-09T06:49:34.734653+00:00'
youtube_status: NOT_FOUND
youtube_search_query: Státní okresní archiv Rokycany official
youtube_search_timestamp: '2025-12-09T09:30:57.912188+00:00'
logo_enrichment:
enrichment_timestamp: '2025-12-24T11:33:09.861321+00:00'
source_url: http://www.soaplzen.cz/soka-ro
extraction_method: crawl4ai
claims:
- claim_type: favicon_url
claim_value: http://www.soaplzen.cz/sites/default/files/easybreeze_favicon.ico
source_url: http://www.soaplzen.cz/soka-ro
css_selector: '[document] > html.js > head > link'
retrieved_on: '2025-12-24T11:33:09.861321+00:00'
extraction_method: crawl4ai_link_rel
favicon_type: image/x-icon
favicon_sizes: ''
summary:
total_claims: 1
has_primary_logo: false
has_favicon: true
has_og_image: false
favicon_count: 1