glam/data/custodian.backup.20251230/CZ-10-CES-A-ACNB.yaml
2025-12-30 23:07:03 +01:00

416 lines
18 KiB
YAML
Raw Permalink Blame History

This file contains invisible Unicode characters

This file contains invisible Unicode characters that are indistinguishable to humans but may be processed differently by a computer. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

original_entry:
name: Archiv České národní banky
institution_type: ARCHIVE
source: CH-Annotator (czech_unified_ch_annotator.yaml)
identifiers:
- &id001
identifier_scheme: ARON_UUID
identifier_value: 0ff35966-32d7-49d4-a831-6d7b4c5e1a25
identifier_url: https://portal.nacr.cz/aron/apu/0ff35966-32d7-49d4-a831-6d7b4c5e1a25
- &id002
identifier_scheme: INSTITUTION_CODE
identifier_value: '610000100'
- &id003
identifier_scheme: Wikidata
identifier_value: Q101474226
identifier_url: https://www.wikidata.org/wiki/Q101474226
- &id004
identifier_scheme: VIAF
identifier_value: '243153061341819202160'
identifier_url: https://viaf.org/viaf/243153061341819202160
locations: []
processing_timestamp: '2025-12-06T23:37:43.808720+00:00'
ghcid:
ghcid_current: CZ-10-CES-A-ACNB
ghcid_original: XX-XX-XXX-A-AČNB
ghcid_uuid: 3cc40155-ccf1-5b12-9762-70e0351fa42a
ghcid_uuid_sha256: c6d6fdf2-dc12-81ad-908b-2e5919ba1e90
ghcid_numeric: 14327918484041920941
record_id: 12145566-42ba-4136-a969-2925528c2b6d
generation_timestamp: '2025-12-06T23:37:43.808720+00:00'
location_resolution:
country_code: CZ
region_code: '10'
city_code: CES
method: CH_ANNOTATOR_TOP_SET
resolution_timestamp: '2025-12-07T00:19:32.878161+00:00'
region_name: CZ-10
iso_code_source: CZ-10
city_name: Ceske Budejovice
geonames_id: 3077916
feature_code: PPLA
extracted_toponym: České
latitude: 48.97447
longitude: 14.47434
ghcid_history:
- previous_ghcid_component: CB
new_ghcid_component: CES
change_date: '2025-12-20T19:55:24Z'
reason: 'Fixed 2-letter city code to proper 3-letter code per AGENTS.md. City: Ceske Budejovice'
- ghcid: CZ-10-CB-A-ACNB
ghcid_numeric: 14327918484041920941
valid_from: '2025-12-08T11:21:41.224062+00:00'
reason: 'Normalized diacritics to ASCII per ABBREV-DIACRITICS rule (was: CZ-10-CB-A-AČNB)'
- ghcid: XX-XX-XXX-A-AČNB
ghcid_numeric: 9883339915281641109
valid_from: '2025-12-06T23:37:43.808720+00:00'
reason: Initial GHCID from CH-Annotator (czech_unified_ch_annotator.yaml)
valid_to: '2025-12-08T11:21:41.224062+00:00'
- ghcid: CZ-XX-XXX-A-AČNB
valid_from: '2025-12-06T23:54:40.176432+00:00'
reason: 'Country resolved via Wikidata P17: XX→CZ'
- ghcid: CZ-10-XXX-A-AČNB
valid_from: '2025-12-07T00:04:46.174940+00:00'
reason: 'Region resolved via Wikidata P131: XX->10 (CZ-10)'
- ghcid: CZ-10-CB-A-AČNB
valid_from: '2025-12-07T00:19:32.878169+00:00'
reason: 'Location resolved via CH-Annotator TOP.SET extraction: České -> Ceske Budejovice (GeoNames:3077916)'
custodian_name:
claim_type: custodian_name
claim_value: Archiv České národní banky
source_type: ch_annotator
identifiers:
- identifier_scheme: GHCID
identifier_value: CZ-10-CB-A-ACNB
- identifier_scheme: GHCID_UUID
identifier_value: 3cc40155-ccf1-5b12-9762-70e0351fa42a
- identifier_scheme: GHCID_UUID_SHA256
identifier_value: c6d6fdf2-dc12-81ad-908b-2e5919ba1e90
- identifier_scheme: GHCID_NUMERIC
identifier_value: '14327918484041920941'
- identifier_scheme: RECORD_ID
identifier_value: 12145566-42ba-4136-a969-2925528c2b6d
- *id001
- *id002
- *id003
- *id004
provenance:
data_source: API_SCRAPING
data_tier: TIER_1_AUTHORITATIVE
extraction_date: '2025-11-19T11:35:45.743421+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 2025-12-07T00:04:46Z: XX->10 via Wikidata P131 (CZ-10)'
- 'Location resolved 2025-12-07T00:19:32Z: CH-Annotator TOP.SET extraction ''České'' -> Ceske Budejovice (GeoNames:3077916, Region:31)'
- 'YouTube/Google Maps enrichment 2025-12-08T19:44:56Z: Maps: State Regional Archive Ceske Budejovice (conf: 0.90); YouTube: not found'
- Canonical location added via normalize_custodian_files.py on 2025-12-08T23:48:03Z
- Canonical location added via normalize_custodian_files.py on 2025-12-09T06:49:27Z
schema_version: 2.0.0
enrichment_provenance:
wikidata_enrichment:
content_hash: sha256-1uT08DLQVS/HAowBBTOC4JeZqFL9fwawPQjqZSME5Ak=
verified_at: '2025-12-28T19:58:20.669588+00:00'
wasDerivedFrom: https://www.wikidata.org/wiki/Q101474226
google_maps_enrichment:
content_hash: sha256-YpEfW3jKjURBld1p+xgIWtTnmMZ3QHDjo94QK2btTj4=
verified_at: '2025-12-28T19:58:20.669696+00:00'
provenance_schema_version: '2.0'
standards_compliance:
- W3C PROV-O
- W3C SRI (content hashes)
generated_at: '2025-12-28T19:58:20.669710+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
timestamp: '2025-11-19T11:35:45.743421+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: 0.85
verified: false
verification_date:
verified_by:
entity_claims:
- claim_type: full_name
claim_value: Archiv České národní banky
property_uri: skos:prefLabel
provenance:
namespace: glam
path: /files/czech_unified.yaml
timestamp: '2025-11-19T11:35:45.743421+00:00'
agent: claude-conversation
context_convention: ch_annotator-v1_7_0
confidence: 0.85
- claim_type: institution_type
claim_value: ARCHIVE
property_uri: rdf:type
provenance:
namespace: glam
path: /files/czech_unified.yaml
timestamp: '2025-11-19T11:35:45.743421+00:00'
agent: claude-conversation
context_convention: ch_annotator-v1_7_0
confidence: 0.95
- claim_type: wikidata_id
claim_value: Q101474226
property_uri: owl:sameAs
provenance:
namespace: wikidata
path: /entity/Q101474226
timestamp: '2025-11-19T11:35:45.743421+00:00'
agent: claude-conversation
context_convention: ch_annotator-v1_7_0
confidence: 0.98
- claim_type: location_settlement
claim_value: Ceske Budejovice
property_uri: schema:location
hypernym_code: TOP.SET
hypernym_label: SETTLEMENT
provenance:
namespace: geonames
path: /geonames/3077916
timestamp: '2025-12-07T00:19:32.878173+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: České
method: pattern_matching
integration_note:
created_from: czech_unified_ch_annotator.yaml
creation_date: '2025-12-06T23:37:43.808720+00:00'
creation_method: create_custodian_from_ch_annotator.py
wikidata_enrichment:
wikidata_entity_id: Q101474226
api_metadata:
api_endpoint: https://www.wikidata.org/w/rest.php/wikibase/v1
fetch_timestamp: '2025-12-08T23:41:03.420501+00:00'
user_agent: GLAMDataExtractor/1.1 (glam-data@example.com) Python/httpx
enrichment_version: 2.0_full
properties_found:
- P31
- P968
- P159
- P17
- P361
- P18
- P214
wikidata_labels:
cs: Archiv České národní banky
wikidata_descriptions:
cs: český specializovaný archiv
wikidata_aliases:
cs:
- Archiv ČNB
wikidata_sitelinks:
cswiki: Archiv České národní banky
wikidata_classification:
instance_of: &id005
- id: Q101470010
label: specialized archives
description: type of archives in Czechia
- id: Q52718263
label: bank archive
description: ''
wikidata_instance_of: *id005
wikidata_location:
headquarters_location:
id: Q973974
label: Prague 1
description: administrative district, municipal district and municipal part of Prague
country: &id006
id: Q213
label: Czech Republic
description: country in Central Europe
wikidata_country: *id006
wikidata_organization:
part_of:
id: Q251062
label: Czech National Bank
description: the central bank and financial market supervisor in the Czech Republic
wikidata_media:
image: Banque nationale tchèque Façade principale.jpg
wikidata_image: Banque nationale tchèque Façade principale.jpg
wikidata_contact:
email: mailto:archiv@cnb.cz
_provenance:
content_hash:
algorithm: sha256
value: sha256-1uT08DLQVS/HAowBBTOC4JeZqFL9fwawPQjqZSME5Ak=
scope: enrichment_section
computed_at: '2025-12-28T19:58:20.669588+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/Q101474226
verification:
status: verified
last_verified: '2025-12-28T19:58:20.669596+00:00'
google_maps_enrichment:
place_id: ChIJa7L6-clPc0cR-V_8UYGa4KE
name: State Regional Archive Ceske Budejovice
fetch_timestamp: '2025-12-08T19:44:50.639672+00:00'
api_status: OK
coordinates:
latitude: 48.9764677
longitude: 14.4845555
formatted_address: 40, Rudolfovská tř. 70, 370 01 České Budějovice-České Budějovice 1, Czechia
short_address: Rudolfovská tř. 70, České Budějovice 1
phone_local: 386 701 214
phone_international: +420 386 701 214
website: https://www.ceskearchivy.cz/statni-okresni-archivy/ceske-budejovice/soka-cb-uvod
google_place_types:
- point_of_interest
- establishment
business_status: OPERATIONAL
rating: 4.9
total_ratings: 15
reviews:
- author_name: Hana Dvořáková
author_uri: https://www.google.com/maps/contrib/106223614438373881734/reviews
rating: 5
relative_time_description: 9 months ago
text: Hello, we attended Eleonore's lecture yesterday and it was great. Beautiful. I have never experienced such a beautiful lecture.
publish_time: '2025-02-26T09:05:14.246458Z'
- author_name: Jakub Bouček (Opravdové příběhy)
author_uri: https://www.google.com/maps/contrib/109262906392895391758/reviews
rating: 5
relative_time_description: 7 years ago
text: 'State archives are one of the places where you can find real information about the history of a particular region, and the České Budějovice archive is a good example of this.
So if you want to find out details about the history of the city and its surroundings, the archive is the right place.'
publish_time: '2018-03-31T13:23:16.449Z'
- author_name: Hana Havlova
author_uri: https://www.google.com/maps/contrib/109085353083285723508/reviews
rating: 4
relative_time_description: 9 months ago
text:
publish_time: '2025-03-02T13:55:04.823721Z'
- author_name: Tomáš Bína
author_uri: https://www.google.com/maps/contrib/103342603459226127712/reviews
rating: 5
relative_time_description: a year ago
text:
publish_time: '2024-11-27T04:07:39.599965Z'
- author_name: Karel Halla
author_uri: https://www.google.com/maps/contrib/107629645487979595240/reviews
rating: 5
relative_time_description: a year ago
text:
publish_time: '2024-11-10T19:38:06.688202Z'
opening_hours:
open_now: false
weekday_text:
- 'Monday: 8:00AM4:00PM'
- 'Tuesday: Closed'
- 'Wednesday: 8:00AM4:00PM'
- 'Thursday: Closed'
- 'Friday: Closed'
- 'Saturday: Closed'
- 'Sunday: Closed'
photo_count: 4
photos_metadata:
- name: places/ChIJa7L6-clPc0cR-V_8UYGa4KE/photos/AZLasHoAI_z6rQO_GKRx_hi5E0bOntWT-cvXlr_bfmcRlLNZhn5XpMFLIXDphfk2fkigYkCFA5b-D7LcaZV04A838knL4Y1VeYn4fh8fDcfbyuUE_nWjDyl2JADcUYfHy7fSGt1WklFz-qTRi_LyVOw7yLbslbGy9Qsl6zWkKVkCoR1TVwfBAD3h_69mYG3fkOSoP9meyCcgASAIjhM67JZtQRDtL3avekEf6ee8q0Dlu94-6R1AtW4o_fAGGQnDmL1sqCO9YLoYAHLFIkGpO6AM4GpHxwXn8B7jGxdwPGIjaJrKDN9CJEHAlZIBqtM6YygmbVs7Fzg7f5l-bkIgU_Y0OP6xuhK7iGQ3Bxt0yfm2iZtz5V1Qd5LHmAs6FfcAvZWLEX3SAoGkEkBr4tRgYATt1rYc9jEQZGfdvzOzHEw2Hw0iw3v7
height: 3264
width: 2448
- name: places/ChIJa7L6-clPc0cR-V_8UYGa4KE/photos/AZLasHo-yhngL7MtC2x18FI5YfQ5Zfe_SkNJs5Ewq8QKP7TvEthN-Ef7pUig0AT-sYyZierkrNELr7YYfBddGt6vkerb_pDNRRfRqKtzyG_3pLi5aNP_B5XcbkBuUtHbYImJmNMniTJY7CTqkj1FuGVZadmBjJJkzdpecEKLy3C5XcRJab7OMv_Zg0L_VWyiJwHPm65izE_NfehzgMLqQLAcvUb5vOF0Kyho5cOrwg_hth3jaE2mZUDBYF8-iC-ArLU2x5GnwCfK1mZmjLIHwo2ZETBd3H-aaJg8XqIu-_xs4YS914Z4eUXsp6bLXedA5A6dyRj8jY0BxWL4CF6x2SweoPTWVNzLCmczdBkJLqEx-rK1glzzyggbPfao6LiZTRJd5mfL4GDvbkp3BFB_ntoLQDanj1Ze9IilV5WYI5rl_R2pAQ
height: 4128
width: 3096
- name: places/ChIJa7L6-clPc0cR-V_8UYGa4KE/photos/AZLasHozq8XE4aeuxjHauCegac3MJio4hzWtjB5gccMStof8CdC0cZ9vglo2jFOXmtW9J9IWl6AWkyUUB7vVqB14K4uvdxp1BZbG71fTLbG3bdVvaMZhP0hkzCbkBBxCatFA-EqBWthOQLU5RrVwgMy20ZpZFDVIfHKNGokHKYb42-UpUdbIQI3aGUBokBnJLyg9kdJRqib4rZybu5iZ1blIxxl4o2ChM-Eg1Mcwe67Vm_oIiOoO0UMaEqe7xmfJshufm3zvdV4hM_pLTP3IAwPueMKG0Qfxq6cfaHAmfJHntsuwCh77fxm3_Omv2ZsNN1YnDW78Hx7K_Ptb7qmQuFwPxp3N0mw8bdWF7Km7vubV1A4T_DO3eDdq9PUoguphI1cWFAixfXzrR5AgqDBKuT2Km3nWLq8XZkuxkeyvV1SJuQ-lCA
height: 2448
width: 3264
- name: places/ChIJa7L6-clPc0cR-V_8UYGa4KE/photos/AZLasHpPAMfLGU5VihcKLU_6wjKif8zTUp8WouFO8tqoQIYDW9t_XD7IJXpfXFJ-TRX4LzkTEoZubEcyxQI1QRsrzCOEkgZmarrcF8So2VWCAe19HujuKEeKw_BU9aLscHPkoMJphPauGeNBFBepQuq6GDLiCWrq_gZCRkjYukjyif9uge3piJpTozizikyni5Cjj7c0GsV6OfKF29YKJNLC22GtqHjdOYdTK7JU6QgQ4j_Uwuu3E6DGdJlNmqb64CWdmHH1pGVRVCxIaFoRCzQgBAUgHVC8s9zSheY-xe_U8PGwYLB63ANKmEhJXBVRg2YjqbR0ThXztpGeZ7H-srHuagV3zXNgUOSVeQLVNwMas5c-sjWZr2KGkh4FjKyxLWQsGy_KcsqMNWBPZc7HpQ4GMccj17Y__pFRArmKomd_-2XYvA
height: 4032
width: 3024
google_maps_url: https://maps.google.com/?cid=11664492915106537465&g_mp=Cidnb29nbGUubWFwcy5wbGFjZXMudjEuUGxhY2VzLlNlYXJjaFRleHQQAhgEIAA
llm_verification:
is_match: true
confidence: 0.9
entity_type: GRP.HER
reasoning: '1. NAME MATCH: Partial but strong match. The source is ''Archiv České národní banky'' (Archive of the Czech National Bank), while the candidate is ''State Regional Archive Ceske Budejovice''. Although the names differ, both are archives, and the source Wikidata item points to ''Státní oblastní archiv v Českých Budějovicích'', which translates directly to the candidate''s name. 2. LOCATION MATCH: Perfect match. Both are in České Budějovice, Czechia. 3. TYPE MATCH: The Google Place types (''point_of_interest'', ''establishment'') are generic, but the name ''Archive'' and the website (ceskearchivy.cz) confirm it is an archive, which is a valid heritage type. 4. ENTITY TYPE: The institution is an archive, which falls under the definition of a heritage institution (GRP.HER).'
agent: glm-4.6
verified: true
ch_annotator_version: ch_annotator-v1_7_0
_provenance:
content_hash:
algorithm: sha256
value: sha256-YpEfW3jKjURBld1p+xgIWtTnmMZ3QHDjo94QK2btTj4=
scope: enrichment_section
computed_at: '2025-12-28T19:58:20.669696+00:00'
prov:
wasDerivedFrom: https://maps.googleapis.com/maps/api/place/details/json?place_id=ChIJa7L6-clPc0cR-V_8UYGa4KE
generatedAtTime: '2025-12-08T19:44:50.639672+00:00'
wasGeneratedBy:
'@type': prov:Activity
name: google_maps_api_fetch
used: https://maps.googleapis.com/maps/api/place
verification:
status: verified
last_verified: '2025-12-28T19:58:20.669702+00:00'
google_maps_status: SUCCESS
youtube_status: NOT_FOUND
youtube_search_query: Archiv České národní banky official
youtube_search_timestamp: '2025-12-08T19:44:56.355247+00:00'
location:
latitude: 48.9764677
longitude: 14.4845555
coordinate_provenance:
source_type: GOOGLE_MAPS
source_path: google_maps_enrichment.coordinates
original_timestamp: '2025-12-08T19:44:50.639672+00:00'
entity_id: ChIJa7L6-clPc0cR-V_8UYGa4KE
city: Ceske Budejovice
region: CZ-10
region_code: '10'
country: CZ
street_address: Rudolfovská tř. 70, České Budějovice 1
formatted_address: 40, Rudolfovská tř. 70, 370 01 České Budějovice-České Budějovice 1, Czechia
geonames_id: 3077916
feature_code: PPLA
normalization_timestamp: '2025-12-09T06:49:27.380425+00:00'
logo_enrichment:
enrichment_timestamp: '2025-12-23T20:18:24.032330+00:00'
source_url: https://www.ceskearchivy.cz/statni-okresni-archivy/ceske-budejovice/soka-cb-uvod
extraction_method: crawl4ai
claims:
- claim_type: logo_url
claim_value: https://www.ceskearchivy.cz/images/INST_logo.png
source_url: https://www.ceskearchivy.cz/statni-okresni-archivy/ceske-budejovice/soka-cb-uvod
css_selector: '#mod-custom206 > p > a > img'
retrieved_on: '2025-12-23T20:18:24.032330+00:00'
extraction_method: crawl4ai_header_logo
detection_confidence: high
alt_text: ''
- claim_type: favicon_url
claim_value: https://www.ceskearchivy.cz/favicon.ico
source_url: https://www.ceskearchivy.cz/statni-okresni-archivy/ceske-budejovice/soka-cb-uvod
css_selector: '[document] > html > head > link:nth-of-type(3)'
retrieved_on: '2025-12-23T20:18:24.032330+00:00'
extraction_method: crawl4ai_link_rel
favicon_type: image/vnd.microsoft.icon
favicon_sizes: ''
- claim_type: og_image_url
claim_value: https://www.ceskearchivy.cz/administrator/cache/preview/80b931d60f4be56fcd0c341aab8b9bc2.jpg
source_url: https://www.ceskearchivy.cz/statni-okresni-archivy/ceske-budejovice/soka-cb-uvod
css_selector: '[document] > html > head > meta:nth-of-type(7)'
retrieved_on: '2025-12-23T20:18:24.032330+00:00'
extraction_method: crawl4ai_meta_og
summary:
total_claims: 3
has_primary_logo: true
has_favicon: true
has_og_image: true
favicon_count: 1