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

356 lines
16 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 Národního bezpečnostního úřadu
institution_type: ARCHIVE
source: CH-Annotator (czech_unified_ch_annotator.yaml)
identifiers:
- &id001
identifier_scheme: ARON_UUID
identifier_value: cc5df131-2382-4d91-afc9-08bf07f75d93
identifier_url: https://portal.nacr.cz/aron/apu/cc5df131-2382-4d91-afc9-08bf07f75d93
- &id002
identifier_scheme: INSTITUTION_CODE
identifier_value: '700000040'
- &id003
identifier_scheme: Wikidata
identifier_value: Q101474244
identifier_url: https://www.wikidata.org/wiki/Q101474244
locations: []
processing_timestamp: '2025-12-06T23:37:44.686147+00:00'
ghcid:
ghcid_current: CZ-10-PRA-A-ANBU
ghcid_original: XX-XX-XXX-A-ANBÚ
ghcid_uuid: f9ce6849-f5a1-5e94-bdf9-89beb99c9758
ghcid_uuid_sha256: e561d472-27e2-8b1f-b161-27d43d726872
ghcid_numeric: 16528725694186928927
record_id: 19d989e2-b2af-4d76-9b06-9dfa2289949e
generation_timestamp: '2025-12-06T23:37:44.686147+00:00'
location_resolution:
country_code: CZ
region_code: 10
city_code: PRA
method: WIKIDATA_LOCATION_RESEARCH
resolution_timestamp: '2025-12-06T23:54:40.395769+00:00'
resolution_notes: National Security Authority Archive in Prague (national security office)
ghcid_history:
- ghcid: CZ-10-PRA-A-ANBU
ghcid_numeric: 16528725694186928927
valid_from: '2025-12-08T11:21:26.031616+00:00'
reason: 'Normalized diacritics to ASCII per ABBREV-DIACRITICS rule (was: CZ-10-PRA-A-ANBÚ)'
- ghcid: XX-XX-XXX-A-ANBÚ
ghcid_numeric: 5515495395228206163
valid_from: '2025-12-06T23:37:44.686147+00:00'
reason: Initial GHCID from CH-Annotator (czech_unified_ch_annotator.yaml)
valid_to: '2025-12-08T11:21:26.031616+00:00'
- ghcid: CZ-XX-XXX-A-ANBÚ
valid_from: '2025-12-06T23:54:40.395776+00:00'
reason: 'Country resolved via Wikidata P17: XX→CZ'
- ghcid: CZ-10-PRA-A-ANBÚ
valid_from: '2025-12-07T12:36:58.326536+00:00'
reason: 'Location resolved via Wikidata research: Prague, region 10'
custodian_name:
claim_type: custodian_name
claim_value: Archiv Národního bezpečnostního úřadu
source_type: ch_annotator
identifiers:
- identifier_scheme: GHCID
identifier_value: CZ-10-PRA-A-ANBU
- identifier_scheme: GHCID_UUID
identifier_value: f9ce6849-f5a1-5e94-bdf9-89beb99c9758
- identifier_scheme: GHCID_UUID_SHA256
identifier_value: e561d472-27e2-8b1f-b161-27d43d726872
- identifier_scheme: GHCID_NUMERIC
identifier_value: '16528725694186928927'
- identifier_scheme: RECORD_ID
identifier_value: 19d989e2-b2af-4d76-9b06-9dfa2289949e
- *id001
- *id002
- *id003
provenance:
data_source: API_SCRAPING
data_tier: TIER_1_AUTHORITATIVE
extraction_date: '2025-11-19T11:35:45.745234+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'
- Removed incorrect wikidata_enrichment on 2025-12-08T08:18:45.454454+00:00. Re-enrichment required with proper matching.
- 'YouTube/Google Maps enrichment 2025-12-08T19:46:08Z: Maps: National Security Authority (conf: 1.00); YouTube: not found'
- Canonical location added via normalize_custodian_files.py on 2025-12-08T23:48:04Z
- 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-my5Ych8wNnxvqwvpEZgmUraK/Aoq7ueO4dRUrwBVQnA=
verified_at: '2025-12-28T19:58:21.066616+00:00'
wasDerivedFrom: https://www.wikidata.org/wiki/Q101474244
google_maps_enrichment:
content_hash: sha256-+Kt0w/1v5UZw5FsC7r3xQZHxK7O/mr7Z1M61qtyFKl4=
verified_at: '2025-12-28T19:58:21.066717+00:00'
provenance_schema_version: '2.0'
standards_compliance:
- W3C PROV-O
- W3C SRI (content hashes)
generated_at: '2025-12-28T19:58:21.066730+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: '2025-11-19T11:35:45.745234+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 Národního bezpečnostního úřadu
property_uri: skos:prefLabel
provenance:
namespace: glam
path: /files/czech_unified.yaml
timestamp: '2025-11-19T11:35:45.745234+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: '2025-11-19T11:35:45.745234+00:00'
agent: claude-conversation
context_convention: ch_annotator-v1_7_0
confidence: 0.95
- claim_type: wikidata_id
claim_value: Q101474244
property_uri: owl:sameAs
provenance:
namespace: wikidata
path: /entity/Q101474244
timestamp: '2025-11-19T11:35:45.745234+00:00'
agent: claude-conversation
context_convention: ch_annotator-v1_7_0
confidence: 0.98
integration_note:
created_from: czech_unified_ch_annotator.yaml
creation_date: '2025-12-06T23:37:44.686147+00:00'
creation_method: create_custodian_from_ch_annotator.py
wikidata_enrichment:
wikidata_entity_id: Q101474244
api_metadata:
api_endpoint: https://www.wikidata.org/w/rest.php/wikibase/v1
fetch_timestamp: '2025-12-08T23:41:13.949211+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
wikidata_labels:
cs: Archiv Národního bezpečnostního úřadu
wikidata_descriptions:
cs: český specializovaný archiv
wikidata_classification:
instance_of: &id004
- id: Q101470010
label: specialized archives
description: type of archives in Czechia
- id: Q101475797
label: security archives
description: type of archives in Czechia
wikidata_instance_of: *id004
wikidata_location:
headquarters_location:
id: Q1085
label: Prague
description: capital city of the Czech Republic
country: &id005
id: Q213
label: Czech Republic
description: country in Central Europe
wikidata_country: *id005
wikidata_organization:
part_of:
id: Q12041615
label: National Security Agency
description: of the Czech Republic
wikidata_contact:
email: mailto:archiv@nbu.cz
_provenance:
content_hash:
algorithm: sha256
value: sha256-my5Ych8wNnxvqwvpEZgmUraK/Aoq7ueO4dRUrwBVQnA=
scope: enrichment_section
computed_at: '2025-12-28T19:58:21.066616+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/Q101474244
verification:
status: verified
last_verified: '2025-12-28T19:58:21.066624+00:00'
google_maps_enrichment:
place_id: ChIJCWBw-KuVC0cRpPyrIaE7dZQ
name: National Security Authority
fetch_timestamp: '2025-12-08T19:46:00.504221+00:00'
api_status: OK
coordinates:
latitude: 50.0697572
longitude: 14.385160200000001
formatted_address: Na Popelce 16/2, 150 06 Praha 5, Czechia
short_address: Na Popelce 16/2, Praha 5
phone_local: 257 283 111
phone_international: +420 257 283 111
website: http://www.nbu.cz/
google_place_types:
- local_government_office
- government_office
- point_of_interest
- establishment
primary_type: local_government_office
business_status: OPERATIONAL
rating: 4.1
total_ratings: 9
reviews:
- author_name: Honza Kralovič
author_uri: https://www.google.com/maps/contrib/108401151967217574722/reviews
rating: 4
relative_time_description: 9 years ago
text: Man in black
publish_time: '2016-02-25T12:12:49.224Z'
- author_name: Jiri Randa
author_uri: https://www.google.com/maps/contrib/105428557309487306330/reviews
rating: 4
relative_time_description: 6 years ago
text: Beer was already being brewed here at the end of the 18th century, and the Košířský brewery was successful. At the end of the 19th century, its annual output was 40,000 hl. After the First World War, things got worse and worse, and competition grew stronger. The end came in 1934... The buildings themselves survived the change of owners and are in good condition today. They represent a nice example of industrial buildings of the time, even with a preserved factory chimney.
publish_time: '2019-10-17T15:05:18.213430Z'
- author_name: Ivo Novotný
author_uri: https://www.google.com/maps/contrib/104107991095760596778/reviews
rating: 5
relative_time_description: 3 years ago
text: Everything is running according to schedule and rules.
publish_time: '2022-10-18T08:49:37.405754Z'
- author_name: Honza Mac
author_uri: https://www.google.com/maps/contrib/106748621551886331403/reviews
rating: 3
relative_time_description: 10 years ago
text: Trust, but verify.
publish_time: '2015-11-20T13:13:32.757Z'
- author_name: Zdenka Stojarová
author_uri: https://www.google.com/maps/contrib/115961268043495815492/reviews
rating: 5
relative_time_description: a month ago
text:
publish_time: '2025-11-08T09:44:25.047006144Z'
opening_hours:
open_now: false
weekday_text:
- 'Monday: 8:00AM5:00PM'
- 'Tuesday: 8:00AM2:00PM'
- 'Wednesday: 8:00AM5:00PM'
- 'Thursday: 8:00AM2:00PM'
- 'Friday: 8:00AM1:00PM'
- 'Saturday: Closed'
- 'Sunday: Closed'
photo_count: 5
photos_metadata:
- name: places/ChIJCWBw-KuVC0cRpPyrIaE7dZQ/photos/AZLasHqg44CbFS1Di59Z0Wa5U-_A2jd38kgXsNKA1sEG-CjL2nOz1BPuievBslH12MQ18WIeXFbcDxtbAF2_Uhx9O75iFdAtnyUE-9k6zLg2lHOzviuHy6BJJXxuYKznu9jn1o1Lk_hGnPP9tV5biYKuxds0jN7va3xRxhkI8SHSEDpvb5fW54sm30iKSXDlTj2LqGYMMryvO5dvGMXoTG5b42xjIDOTe29L2l1sCpIfqahL0qbxI3i_UJll8u-jdo3f0bOkl-443T6Sf8MTFwOI-C4yLovDTLlZ2NIxYhlgdgo6kRruNGQ-g-KY3NUsepMTiFT-r52Mi9AmiqbkVLKmOmN0oXaKJgX9rKjBUANpB0NZ6m4lFtVQZsMPslayHgu1FmYpkYxShMGab0G31wEy1OrnbjdOVRODnnnbXWg9ylkk0IQ
height: 3120
width: 4160
- name: places/ChIJCWBw-KuVC0cRpPyrIaE7dZQ/photos/AZLasHqe1AkC2jcGbkZqbbiGnTqS1HoEX5Sfx0b9habeE4Gw-C6El2slrIO_ODMO1Eq7YgjD-LZZ-kOtBoGHwAPN5m-he7N5hB87ch0yBERNYaYU9wkqOlp-TvLZu_woNnxyY4BrGBPGbPm2VpZFLWbffDW3eNkjTnbMWSkeTmZm5016EysiWeYY9j5kOehoPKAGm5xc5OxfUr0e5r9DAGZ_iqzMOLtG9qooV10R3pzBzAwaAX1Q-FCgdk1KHfJHH5imRHkLn4HnpMZolL_9WQmI2nvYx4LooHdYs4LbHfBxLPk6L6gvv_uRfigu1bih-mvCtWHJ-0L3afvqjRFnbJfRGyvyzQlkf2nyDAiRrb6bPw46SSfqMI8wYiiPc84oul6CUrPQQ1LHk0hegMh644EBFKqGZPaV5cCtRzsuiZFnQbyctQ
height: 2160
width: 3840
- name: places/ChIJCWBw-KuVC0cRpPyrIaE7dZQ/photos/AZLasHqipWyv2ksmzyvjgEv277rllgDeaOlb0EMQtil5JP1inBrjXo99BvjQaJramVUgTqHnPgKByGfZWEy_FHOEjb_qzeMB85ye2FukTQYuQApSOTfnhVZGtYvZo3yiAZOHDBgUskaQBum_YY3-Xxf0pHHh6p-5PXmS_G3RWfkrLxx8c9WtBazqymkK0Ig7-WR5vII0n6Dxof7cJ8DTwa4PdXuohyIqNdxzx6bikR7ovtboGFFBbWw1HOq1ly2Jb3CywACCvVj_U203eYcCXydgL2_sFv0iaQv2FVgOc0OI_aIkO7DzLNpdtoaOR9p0F7lyPLV6lZOzu3_684FuTKG4IRzhMYoA3nqsrqxwACnrf1Qb-zQNRcEs_gGKSigdRO5BkJ6IXXnF6hDjZtxyK2lebmK1e0qicONPvn2P-8rpi6Wq1N6o
height: 3024
width: 4032
- name: places/ChIJCWBw-KuVC0cRpPyrIaE7dZQ/photos/AZLasHpSoy9LrKqFo8hV0hdKx_h2_BCpFcSFO7Lipm1RxtnnSRaIgL3EdgCN-sZVDOytFqHaL3fLP-p20pfbyr4O1jLSJmXtrCV4lwQstooeSpuU39rsxuLDxAGfEeRjOlDGqsF9EnIw7Hw55YGRNGbdM4TNbCAyKFVJzMDdR7pPBa3h9PKcfyfzb2x-HHOZX173m8gSPOMAvrtIXFFgLxpys8o9wv1vSscwUg7Bu5zYRas2Z3Xx2PkRDMuZ5eCXdcvlU65-TEfLrkBSwT_Lw8qMvgWe27d4KlkDBe47CNhGa0oV03WIgO6dqrnqA6Uq6cQSiIl7Vdga2zHIeRw1zYldH7PcFx_SCtM64LuU9Z96KkCN7pzp65hHJB1FZDIOPKO6XIWK5P0EpfihGkUtGlwUOTHw4nfmso-Fe2jk5h8V-xyJSJ4
height: 3024
width: 4032
- name: places/ChIJCWBw-KuVC0cRpPyrIaE7dZQ/photos/AZLasHqXZ7YKWZ3tX1ztiGRIXaztqvrAF_Wj9yok7sDkOtAsi0nPmBYzUbsnCZBE_HZ-ai3ke8xiKNbT5nmeT5Hk7N6VliLs3e17c7cCJcH_pwRRZhrPUItZTWHRFLXd8lLr-I_kCYMiwrJzr9VFjH9s2-NlVLQbpp8Sfhklz0wsoYixanwrmKHtFcPYKwbaSzauQqIvDsU52Hyn37zA2-uHWKM2GRGKleIVqypWguIFZNsyUMj8oFCWA_XeOmm_OYHXS3UNhr0GsjQP5npHtMZ_8FuV2sINQ28jnIUob6M8Q-JB9jMmCQkcmlVEROqI0OVlt9jbXhce3C2qaLQscQtengBOqVIh7jcPMHynR6EG1bgjFzmMux-LQHnnYLelbUY8NsUSUiIYk9iZ0974O1wolEVFjQ9ov4w_0XYmwrjH3DU
height: 2992
width: 4000
google_maps_url: https://maps.google.com/?cid=10697522053129174180&g_mp=Cidnb29nbGUubWFwcy5wbGFjZXMudjEuUGxhY2VzLlNlYXJjaFRleHQQAhgEIAA
llm_verification:
is_match: true
confidence: 1.0
entity_type: GRP.HER
reasoning: 'The Google Maps place is a match. 1. NAME MATCH: ''National Security Authority'' is the English translation of ''Národní bezpečnostního úřadu''. The source name, ''Archiv Národního bezpečnostního úřadu'', identifies this place as the archive of that authority. The website ''nbu.cz'' confirms the identity. 2. LOCATION MATCH: The address is in Praha, Czechia, matching the source country (CZ). 3. TYPE MATCH: While the Google Place type is ''local_government_office'', this is not grounds for rejection. The source explicitly identifies the institution as an ''Archiv'', which falls under the GRP.HER definition. 4. ENTITY TYPE: The institution is an archive, a type of heritage custodian.'
agent: glm-4.6
verified: true
ch_annotator_version: ch_annotator-v1_7_0
_provenance:
content_hash:
algorithm: sha256
value: sha256-+Kt0w/1v5UZw5FsC7r3xQZHxK7O/mr7Z1M61qtyFKl4=
scope: enrichment_section
computed_at: '2025-12-28T19:58:21.066717+00:00'
prov:
wasDerivedFrom: https://maps.googleapis.com/maps/api/place/details/json?place_id=ChIJCWBw-KuVC0cRpPyrIaE7dZQ
generatedAtTime: '2025-12-08T19:46:00.504221+00:00'
wasGeneratedBy:
'@type': prov:Activity
name: google_maps_api_fetch
used: https://maps.googleapis.com/maps/api/place
verification:
status: verified
last_verified: '2025-12-28T19:58:21.066722+00:00'
google_maps_status: SUCCESS
youtube_status: NOT_FOUND
youtube_search_query: Archiv Národního bezpečnostního úřadu official
youtube_search_timestamp: '2025-12-08T19:46:08.214471+00:00'
location:
latitude: 50.0697572
longitude: 14.385160200000001
coordinate_provenance:
source_type: GOOGLE_MAPS
source_path: google_maps_enrichment.coordinates
original_timestamp: '2025-12-08T19:46:00.504221+00:00'
entity_id: ChIJCWBw-KuVC0cRpPyrIaE7dZQ
region_code: 10
country: CZ
street_address: Na Popelce 16/2, Praha 5
formatted_address: Na Popelce 16/2, 150 06 Praha 5, Czechia
normalization_timestamp: '2025-12-09T06:49:27.913673+00:00'
logo_enrichment:
enrichment_timestamp: '2025-12-23T20:19:36.697627+00:00'
source_url: http://www.nbu.cz
extraction_method: crawl4ai
claims:
- claim_type: favicon_url
claim_value: http://www.nbu.cz/templates/nbu/favicon.ico
source_url: http://www.nbu.cz
css_selector: '[document] > html > head > link:nth-of-type(2)'
retrieved_on: '2025-12-23T20:19:36.697627+00:00'
extraction_method: crawl4ai_link_rel
favicon_type: image/vnd.microsoft.icon
favicon_sizes: ''
summary:
total_claims: 1
has_primary_logo: false
has_favicon: true
has_og_image: false
favicon_count: 1