262 lines
9.7 KiB
YAML
262 lines
9.7 KiB
YAML
original_entry:
|
|
name: APESP
|
|
institution_type: MIXED
|
|
source: CH-Annotator (latin_american_institutions_AUTHORITATIVE_ch_annotator.yaml)
|
|
identifiers:
|
|
- identifier_scheme: GHCID
|
|
identifier_value: BR-SP-XXX-M-A
|
|
- identifier_scheme: GHCID_NUMERIC
|
|
identifier_value: '3264520367979643668'
|
|
- &id001
|
|
identifier_scheme: OLD_ID
|
|
identifier_value: https://w3id.org/heritage/custodian/br/apesp
|
|
- identifier_scheme: GHCID_UUID
|
|
identifier_value: 655b1801-c3e8-5bcb-8f17-2b8b061f1ba7
|
|
identifier_url: urn:uuid:655b1801-c3e8-5bcb-8f17-2b8b061f1ba7
|
|
- identifier_scheme: GHCID_UUID_SHA256
|
|
identifier_value: 2d4de7fa-7f74-8314-9d73-cecadce05eeb
|
|
identifier_url: urn:uuid:2d4de7fa-7f74-8314-9d73-cecadce05eeb
|
|
- identifier_scheme: RECORD_ID
|
|
identifier_value: 019a58fd-3227-71df-94b8-43f03462af9c
|
|
identifier_url: urn:uuid:019a58fd-3227-71df-94b8-43f03462af9c
|
|
- &id002
|
|
identifier_scheme: OLD_ID
|
|
identifier_value: 3264520367979643668
|
|
locations:
|
|
- country: BR
|
|
region: SÃO PAULO
|
|
processing_timestamp: '2025-12-06T23:39:01.759080+00:00'
|
|
ghcid:
|
|
ghcid_current: BR-SP-SPA-X-A-apesp
|
|
ghcid_original: BR-SA-XXX-X-A-apesp
|
|
ghcid_uuid: 22e3ede7-0116-5f3b-9c4f-de1f5d6b21aa
|
|
ghcid_uuid_sha256: 6f8a8ca2-be79-87bf-c59b-af7cb8ab7080
|
|
ghcid_numeric: 8037391115604289471
|
|
record_id: 0fc16e7e-2236-431c-9f2b-c9cf66b9c5b9
|
|
generation_timestamp: '2025-12-06T23:39:01.759080+00:00'
|
|
location_resolution:
|
|
method: GOOGLE_PLACES_GEONAMES
|
|
country_code: BR
|
|
region_code: SP
|
|
region_name: São Paulo
|
|
city_code: SPA
|
|
city_name: Sao Paulo
|
|
geonames_id: 3448439
|
|
feature_code: PPLA
|
|
google_place_id: ChIJA1WDfVRYzpQRKtVDAI1mGJs
|
|
latitude: -23.5462922
|
|
longitude: -46.6364069
|
|
resolution_date: '2025-12-07T16:39:13.155940+00:00'
|
|
ghcid_history:
|
|
- ghcid: BR-SA-XXX-X-A-apesp
|
|
ghcid_numeric: 8037391115604289471
|
|
valid_from: '2025-12-06T23:39:01.759080+00:00'
|
|
reason: Initial GHCID from CH-Annotator (latin_american_institutions_AUTHORITATIVE_ch_annotator.yaml)
|
|
valid_to: '2025-12-07T16:39:13.155940+00:00'
|
|
- ghcid: BR-SP-SPA-X-A-apesp
|
|
ghcid_numeric: 8037391115604289471
|
|
valid_from: '2025-12-07T16:39:13.155940+00:00'
|
|
reason: 'Location resolved via Google Places + GeoNames: Sao Paulo (SP)'
|
|
custodian_name:
|
|
claim_type: custodian_name
|
|
claim_value: APESP
|
|
source_type: ch_annotator
|
|
identifiers:
|
|
- identifier_scheme: GHCID
|
|
identifier_value: BR-SP-SPA-X-A-apesp
|
|
- identifier_scheme: GHCID_UUID
|
|
identifier_value: 22e3ede7-0116-5f3b-9c4f-de1f5d6b21aa
|
|
- identifier_scheme: GHCID_UUID_SHA256
|
|
identifier_value: 6f8a8ca2-be79-87bf-c59b-af7cb8ab7080
|
|
- identifier_scheme: GHCID_NUMERIC
|
|
identifier_value: '8037391115604289471'
|
|
- identifier_scheme: RECORD_ID
|
|
identifier_value: 0fc16e7e-2236-431c-9f2b-c9cf66b9c5b9
|
|
- *id001
|
|
- *id002
|
|
provenance:
|
|
data_source: CONVERSATION_NLP
|
|
data_tier: TIER_4_INFERRED
|
|
extraction_date: '2025-11-06T08:25:13.555409+00:00'
|
|
extraction_method: 'Created from CH-Annotator file: latin_american_institutions_AUTHORITATIVE_ch_annotator.yaml'
|
|
confidence_score: 0.7
|
|
notes:
|
|
- Canonical location added via normalize_custodian_files.py on 2025-12-08T23:10:54Z
|
|
- Canonical location added via normalize_custodian_files.py on 2025-12-08T23:46:58Z
|
|
- Canonical location added via normalize_custodian_files.py on 2025-12-09T06:48:23Z
|
|
- 'YouTube/Google Maps enrichment 2025-12-09T08:52:14Z: YouTube: not found'
|
|
schema_version: 2.0.0
|
|
enrichment_provenance:
|
|
wikidata_enrichment:
|
|
content_hash: sha256-wgdWqIjQ55jhW+vX4PzPUeB8sZcxEbCGAJzXPPJ6pvw=
|
|
verified_at: '2025-12-28T19:57:38.263778+00:00'
|
|
wasDerivedFrom: https://www.wikidata.org/wiki/Q9630401
|
|
google_maps_enrichment:
|
|
content_hash: sha256-u73Evo1EaBM2SghR5ZdCN3gxXUC4wCDIqw3refJIc7k=
|
|
verified_at: '2025-12-28T19:57:38.263801+00:00'
|
|
provenance_schema_version: '2.0'
|
|
standards_compliance:
|
|
- W3C PROV-O
|
|
- W3C SRI (content hashes)
|
|
generated_at: '2025-12-28T19:57:38.263811+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.MIX
|
|
subtype_label: MIXED
|
|
ontology_class: glam:HeritageCustodian
|
|
alternative_classes:
|
|
- org:FormalOrganization
|
|
- rov:RegisteredOrganization
|
|
- glam:HeritageCustodian
|
|
extraction_provenance:
|
|
namespace: glam
|
|
path: /conversations/2025-09-22T14-40-15-0102c00a-4c0a-4488-bdca-5dd9fb94c9c5
|
|
timestamp: '2025-11-06T08:25:13.555409+00:00'
|
|
agent: claude-conversation
|
|
context_convention: ch_annotator-v1_7_0
|
|
annotation_provenance:
|
|
annotation_agent: opencode-claude-sonnet-4
|
|
annotation_date: '2025-12-06T21:13:56.173868+00:00'
|
|
annotation_method: retroactive CH-Annotator application via batch script
|
|
source_file: latin_american_institutions_AUTHORITATIVE.yaml
|
|
annotation_metadata:
|
|
confidence_score: 0.7
|
|
verified: false
|
|
verification_date:
|
|
verified_by:
|
|
entity_claims:
|
|
- claim_type: full_name
|
|
claim_value: APESP
|
|
property_uri: skos:prefLabel
|
|
provenance:
|
|
namespace: glam
|
|
path: /conversations/2025-09-22T14-40-15-0102c00a-4c0a-4488-bdca-5dd9fb94c9c5
|
|
timestamp: '2025-11-06T08:25:13.555409+00:00'
|
|
agent: claude-conversation
|
|
context_convention: ch_annotator-v1_7_0
|
|
confidence: 0.7
|
|
- claim_type: institution_type
|
|
claim_value: MIXED
|
|
property_uri: rdf:type
|
|
provenance:
|
|
namespace: glam
|
|
path: /conversations/2025-09-22T14-40-15-0102c00a-4c0a-4488-bdca-5dd9fb94c9c5
|
|
timestamp: '2025-11-06T08:25:13.555409+00:00'
|
|
agent: claude-conversation
|
|
context_convention: ch_annotator-v1_7_0
|
|
confidence: 0.95
|
|
- claim_type: ghcid
|
|
claim_value: BR-SP-XXX-M-A
|
|
property_uri: glam:ghcid
|
|
provenance:
|
|
namespace: glam
|
|
path: /conversations/2025-09-22T14-40-15-0102c00a-4c0a-4488-bdca-5dd9fb94c9c5
|
|
timestamp: '2025-11-06T08:25:13.555409+00:00'
|
|
agent: claude-conversation
|
|
context_convention: ch_annotator-v1_7_0
|
|
confidence: 1.0
|
|
integration_note:
|
|
created_from: latin_american_institutions_AUTHORITATIVE_ch_annotator.yaml
|
|
creation_date: '2025-12-06T23:39:01.759080+00:00'
|
|
creation_method: create_custodian_from_ch_annotator.py
|
|
google_maps_enrichment:
|
|
place_id: ChIJA1WDfVRYzpQRKtVDAI1mGJs
|
|
formatted_address: R. Líbero Badaró, 377 - Se, São Paulo - SP, 01009-906, Brazil
|
|
website: http://www.apesp.org.br/
|
|
latitude: -23.5462922
|
|
longitude: -46.6364069
|
|
enriched_at: '2025-12-07T16:39:13.155940+00:00'
|
|
source: Google Places API (New)
|
|
_provenance:
|
|
content_hash:
|
|
algorithm: sha256
|
|
value: sha256-u73Evo1EaBM2SghR5ZdCN3gxXUC4wCDIqw3refJIc7k=
|
|
scope: enrichment_section
|
|
computed_at: '2025-12-28T19:57:38.263801+00:00'
|
|
prov:
|
|
wasDerivedFrom: https://maps.googleapis.com/maps/api/place/details/json?place_id=ChIJA1WDfVRYzpQRKtVDAI1mGJs
|
|
wasGeneratedBy:
|
|
'@type': prov:Activity
|
|
name: google_maps_api_fetch
|
|
used: https://maps.googleapis.com/maps/api/place
|
|
verification:
|
|
status: verified
|
|
last_verified: '2025-12-28T19:57:38.263804+00:00'
|
|
location:
|
|
latitude: -23.5462922
|
|
longitude: -46.6364069
|
|
coordinate_provenance:
|
|
source_type: GHCID_RESOLUTION_DIRECT
|
|
source_path: ghcid.location_resolution
|
|
entity_id: 3448439
|
|
resolution_method: GOOGLE_PLACES_GEONAMES
|
|
city: Sao Paulo
|
|
region: São Paulo
|
|
region_code: SP
|
|
country: BR
|
|
formatted_address: R. Líbero Badaró, 377 - Se, São Paulo - SP, 01009-906, Brazil
|
|
geonames_id: 3448439
|
|
feature_code: PPLA
|
|
normalization_timestamp: '2025-12-09T06:48:23.493590+00:00'
|
|
youtube_status: NOT_FOUND
|
|
youtube_search_query: APESP official
|
|
youtube_search_timestamp: '2025-12-09T08:52:14.818698+00:00'
|
|
wikidata_enrichment:
|
|
wikidata_id: Q9630401
|
|
wikidata_url: https://www.wikidata.org/wiki/Q9630401
|
|
label: Arquivo Público do Estado de São Paulo
|
|
description: archives
|
|
enrichment_timestamp: '2025-01-13T00:00:00Z'
|
|
enrichment_method: manual_wikidata_lookup
|
|
identifiers:
|
|
VIAF: '168183385'
|
|
LCNAF: no2007028161
|
|
official_website: http://www.arquivoestado.sp.gov.br/
|
|
_provenance:
|
|
content_hash:
|
|
algorithm: sha256
|
|
value: sha256-wgdWqIjQ55jhW+vX4PzPUeB8sZcxEbCGAJzXPPJ6pvw=
|
|
scope: enrichment_section
|
|
computed_at: '2025-12-28T19:57:38.263778+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/Q9630401
|
|
generatedAtTime: '2025-01-13T00:00:00Z'
|
|
verification:
|
|
status: verified
|
|
last_verified: '2025-12-28T19:57:38.263783+00:00'
|
|
wikidata_entity_id: Q9630401
|
|
logo_enrichment:
|
|
enrichment_timestamp: '2025-12-22T14:52:37.001646+00:00'
|
|
source_url: http://www.apesp.org.br
|
|
extraction_method: crawl4ai
|
|
claims:
|
|
- claim_type: logo_url
|
|
claim_value: https://apesp.org.br/wp-content/uploads/2015/07/5ecfe5aabf4c7_APESP_marca_1_assinatura_pricipal_cor-1.png
|
|
source_url: http://www.apesp.org.br
|
|
css_selector: '#logo > img.logo-main.scale-with-grid'
|
|
retrieved_on: '2025-12-22T14:52:37.001646+00:00'
|
|
extraction_method: crawl4ai_header_logo
|
|
detection_confidence: high
|
|
alt_text: 5ecfe5aabf4c7_APESP_marca_1_assinatura_pricipal_cor (1)
|
|
- claim_type: favicon_url
|
|
claim_value: https://apesp.org.br/wp-content/uploads/2015/07/favicon-250x250.png
|
|
source_url: http://www.apesp.org.br
|
|
css_selector: '[document] > html.js > head > link:nth-of-type(34)'
|
|
retrieved_on: '2025-12-22T14:52:37.001646+00:00'
|
|
extraction_method: crawl4ai_link_rel
|
|
favicon_type: ''
|
|
favicon_sizes: 192x192
|
|
summary:
|
|
total_claims: 2
|
|
has_primary_logo: true
|
|
has_favicon: true
|
|
has_og_image: false
|
|
favicon_count: 3
|