313 lines
11 KiB
YAML
313 lines
11 KiB
YAML
custodian_name:
|
|
claim_type: custodian_name
|
|
claim_value: Státní okresní archiv Teplice
|
|
source_type: ch_annotator
|
|
original_entry:
|
|
name: Státní okresní archiv Teplice
|
|
institution_type: ARCHIVE
|
|
source: CH-Annotator (czech_unified_ch_annotator.yaml)
|
|
identifiers:
|
|
- &id001
|
|
identifier_scheme: ARON_UUID
|
|
identifier_value: 432578fb-287a-4503-8cca-55763e360c97
|
|
identifier_url: https://portal.nacr.cz/aron/apu/432578fb-287a-4503-8cca-55763e360c97
|
|
- &id002
|
|
identifier_scheme: INSTITUTION_CODE
|
|
identifier_value: '224106010'
|
|
- &id003
|
|
identifier_scheme: Wikidata
|
|
identifier_value: Q53201705
|
|
identifier_url: https://www.wikidata.org/wiki/Q53201705
|
|
- &id004
|
|
identifier_scheme: VIAF
|
|
identifier_value: '314915772'
|
|
identifier_url: https://viaf.org/viaf/314915772
|
|
locations: []
|
|
processing_timestamp: '2025-12-06T23:37:44.076015+00:00'
|
|
ghcid:
|
|
ghcid_current: CZ-42-TEP-A-SOAT-statni_okresni_archiv_teplice
|
|
ghcid_original: XX-XX-XXX-A-SOAT-statni_okresni_archiv_teplice
|
|
ghcid_uuid: d30a8a01-8d1e-511c-b3af-bd130f844b6b
|
|
ghcid_uuid_sha256: 8eece13b-57cc-885c-20f7-c5aa8f2aef52
|
|
ghcid_numeric: 10298854092881807452
|
|
record_id: 463e0f4b-d5c8-461e-95e7-ed6214e2b8dd
|
|
generation_timestamp: '2025-12-06T23:37:44.076015+00:00'
|
|
location_resolution:
|
|
country_code: CZ
|
|
region_code: '42'
|
|
city_code: TEP
|
|
method: CH_ANNOTATOR_TOP_SET
|
|
resolution_timestamp: '2025-12-07T00:19:32.529983+00:00'
|
|
region_name: CZ-42
|
|
iso_code_source: CZ-42
|
|
city_name: Teplice
|
|
geonames_id: 3064288
|
|
feature_code: PPL
|
|
extracted_toponym: Teplice
|
|
latitude: 50.6404
|
|
longitude: 13.82451
|
|
ghcid_history:
|
|
- ghcid: XX-XX-XXX-A-SOAT-statni_okresni_archiv_teplice
|
|
ghcid_numeric: 10298854092881807452
|
|
valid_from: '2025-12-06T23:37:44.076015+00:00'
|
|
reason: Initial GHCID from CH-Annotator (czech_unified_ch_annotator.yaml)
|
|
- ghcid: CZ-XX-XXX-A-SOAT-statni_okresni_archiv_teplice
|
|
valid_from: '2025-12-06T23:54:38.438972+00:00'
|
|
reason: 'Country resolved via Wikidata P17: XX→CZ'
|
|
- ghcid: CZ-42-XXX-A-SOAT-statni_okresni_archiv_teplice
|
|
valid_from: '2025-12-07T00:02:04.902275+00:00'
|
|
reason: 'Region resolved via Wikidata P131: XX->42 (CZ-42)'
|
|
- ghcid: CZ-42-TEP-A-SOAT-statni_okresni_archiv_teplice
|
|
valid_from: '2025-12-07T00:19:32.529989+00:00'
|
|
reason: 'Location resolved via CH-Annotator TOP.SET extraction: Teplice -> Teplice (GeoNames:3064288)'
|
|
identifiers:
|
|
- identifier_scheme: GHCID
|
|
identifier_value: XX-XX-XXX-A-SOAT-statni_okresni_archiv_teplice
|
|
- identifier_scheme: GHCID_UUID
|
|
identifier_value: d30a8a01-8d1e-511c-b3af-bd130f844b6b
|
|
- identifier_scheme: GHCID_UUID_SHA256
|
|
identifier_value: 8eece13b-57cc-885c-20f7-c5aa8f2aef52
|
|
- identifier_scheme: GHCID_NUMERIC
|
|
identifier_value: '10298854092881807452'
|
|
- identifier_scheme: RECORD_ID
|
|
identifier_value: 463e0f4b-d5c8-461e-95e7-ed6214e2b8dd
|
|
- *id001
|
|
- *id002
|
|
- *id003
|
|
- *id004
|
|
provenance:
|
|
data_source: API_SCRAPING
|
|
data_tier: TIER_1_AUTHORITATIVE
|
|
extraction_date: '2025-11-19T11:35:45.743990+00:00'
|
|
extraction_method: 'Created from CH-Annotator file: czech_unified_ch_annotator.yaml'
|
|
confidence_score: 0.85
|
|
notes:
|
|
- 'Country resolved 2025-12-06T23:54:38Z: XX→CZ via Wikidata P17'
|
|
- 'Region resolved 2025-12-07T00:02:04Z: XX->42 via Wikidata P131 (CZ-42)'
|
|
- 'Location resolved 2025-12-07T00:19:32Z: CH-Annotator TOP.SET extraction ''Teplice'' -> Teplice (GeoNames:3064288, 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 2025-12-09T09:31:28Z: YouTube: not found'
|
|
schema_version: 2.0.0
|
|
enrichment_provenance:
|
|
wikidata_enrichment:
|
|
content_hash: sha256-apG9nY0ORDGi6X8W3WpQlKzsxqB9VdhbMg2b36T+3x8=
|
|
verified_at: '2025-12-28T19:59:05.473404+00:00'
|
|
wasDerivedFrom: https://www.wikidata.org/wiki/Q53201705
|
|
provenance_schema_version: '2.0'
|
|
standards_compliance:
|
|
- W3C PROV-O
|
|
- W3C SRI (content hashes)
|
|
generated_at: '2025-12-28T19:59:05.473423+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: '2025-11-19T11:35:45.743990+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 Teplice
|
|
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: '2025-11-19T11:35:45.743990+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: '2025-11-19T11:35:45.743990+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: Q53201705
|
|
property_uri: owl:sameAs
|
|
provenance:
|
|
namespace: wikidata
|
|
path: /entity/Q53201705
|
|
agent: batch-script-create-custodian-from-ch-annotator
|
|
context_convention: ch_annotator-v1_7_0
|
|
source_archived_at: '2025-11-19T11:35:45.743990+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: Teplice
|
|
property_uri: schema:location
|
|
hypernym_code: TOP.SET
|
|
hypernym_label: SETTLEMENT
|
|
provenance:
|
|
namespace: geonames
|
|
path: /geonames/3064288
|
|
timestamp: '2025-12-07T00:19:32.529991+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: Teplice
|
|
method: pattern_matching
|
|
integration_note:
|
|
created_from: czech_unified_ch_annotator.yaml
|
|
creation_date: '2025-12-06T23:37:44.076015+00:00'
|
|
creation_method: create_custodian_from_ch_annotator.py
|
|
wikidata_enrichment:
|
|
wikidata_entity_id: Q53201705
|
|
api_metadata:
|
|
api_endpoint: https://www.wikidata.org/w/rest.php/wikibase/v1
|
|
fetch_timestamp: '2025-12-08T23:43:47.995454+00:00'
|
|
user_agent: GLAMDataExtractor/1.1 (glam-data@example.com) Python/httpx
|
|
enrichment_version: 2.0_full
|
|
properties_found:
|
|
- P31
|
|
- P17
|
|
- P625
|
|
- P214
|
|
- P227
|
|
- P856
|
|
- P361
|
|
- P131
|
|
- P159
|
|
wikidata_labels:
|
|
cs: Státní okresní archiv Teplice
|
|
en: State District Archives Teplice
|
|
wikidata_label_en: State District Archives Teplice
|
|
wikidata_descriptions:
|
|
cs: archiv v Teplicích
|
|
en: archive in Teplice, Czech Republic
|
|
wikidata_description_en: archive in Teplice, Czech Republic
|
|
wikidata_aliases:
|
|
cs:
|
|
- SOkA Teplice
|
|
en:
|
|
- SOkA Teplice
|
|
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: &id007
|
|
id: Q213
|
|
label: Czech Republic
|
|
description: country in Central Europe
|
|
coordinates: &id008
|
|
latitude: 50.6426164
|
|
longitude: 13.8254128
|
|
precision: 1.0e-07
|
|
located_in_admin_entity: &id006
|
|
id: Q146342
|
|
label: Teplice
|
|
description: city in the Ústí nad Labem Region, Czech Republic
|
|
headquarters_location: *id006
|
|
wikidata_country: *id007
|
|
wikidata_located_in: *id006
|
|
wikidata_coordinates: *id008
|
|
wikidata_organization:
|
|
part_of:
|
|
id: Q18920590
|
|
label: State Regional Archives Litoměřice
|
|
description: regional archive
|
|
wikidata_web:
|
|
official_website: http://www.soalitomerice.cz/soka-teplice/
|
|
wikidata_official_website: http://www.soalitomerice.cz/soka-teplice/
|
|
_provenance:
|
|
content_hash:
|
|
algorithm: sha256
|
|
value: sha256-apG9nY0ORDGi6X8W3WpQlKzsxqB9VdhbMg2b36T+3x8=
|
|
scope: enrichment_section
|
|
computed_at: '2025-12-28T19:59:05.473404+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/Q53201705
|
|
verification:
|
|
status: verified
|
|
last_verified: '2025-12-28T19:59:05.473413+00:00'
|
|
location:
|
|
latitude: 50.6426164
|
|
longitude: 13.8254128
|
|
coordinate_provenance:
|
|
source_type: WIKIDATA
|
|
source_path: wikidata_enrichment.wikidata_coordinates
|
|
original_timestamp: '2025-12-08T23:43:47.995454+00:00'
|
|
api_endpoint: https://www.wikidata.org/w/rest.php/wikibase/v1
|
|
entity_id: Q53201705
|
|
city: Teplice
|
|
region: CZ-42
|
|
region_code: '42'
|
|
country: CZ
|
|
geonames_id: 3064288
|
|
feature_code: PPL
|
|
normalization_timestamp: '2025-12-09T06:49:35.826471+00:00'
|
|
youtube_status: NOT_FOUND
|
|
youtube_search_query: Státní okresní archiv Teplice official
|
|
youtube_search_timestamp: '2025-12-09T09:31:28.349086+00:00'
|
|
logo_enrichment:
|
|
enrichment_timestamp: '2025-12-24T21:08:41.082488+00:00'
|
|
source_url: http://www.soalitomerice.cz/soka-teplice
|
|
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-teplice
|
|
css_selector: '[document] > html.td-md-is-chrome > body.post-template-default.single > link:nth-of-type(3)'
|
|
retrieved_on: '2025-12-24T21:08:41.082488+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/sokatp.jpg
|
|
source_url: http://www.soalitomerice.cz/soka-teplice
|
|
css_selector: '[document] > html.td-md-is-chrome > head > meta:nth-of-type(14)'
|
|
retrieved_on: '2025-12-24T21:08:41.082488+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
|