57 lines
1.9 KiB
YAML
57 lines
1.9 KiB
YAML
# LogoEnrichment - Logo and favicon enrichment data from web scraping
|
|
# Created for CustodianSourceFile validation compatibility
|
|
# Creation date: 2026-01-18
|
|
|
|
id: https://nde.nl/ontology/hc/classes/LogoEnrichment
|
|
name: LogoEnrichment
|
|
title: LogoEnrichment
|
|
|
|
prefixes:
|
|
linkml: https://w3id.org/linkml/
|
|
hc: https://nde.nl/ontology/hc/
|
|
schema: http://schema.org/
|
|
prov: http://www.w3.org/ns/prov#
|
|
xsd: http://www.w3.org/2001/XMLSchema#
|
|
|
|
imports:
|
|
- linkml:types
|
|
- ./LogoClaim
|
|
- ./LogoEnrichmentSummary
|
|
default_range: string
|
|
|
|
classes:
|
|
LogoEnrichment:
|
|
description: >-
|
|
Logo and favicon enrichment data extracted from institutional websites
|
|
via web scraping (crawl4ai). Captures logos, favicons, OpenGraph images,
|
|
and other visual brand assets with full provenance tracking.
|
|
|
|
Ontology mapping rationale:
|
|
- class_uri is prov:Entity because this represents enrichment data
|
|
with provenance (timestamps, methods, sources)
|
|
- close_mappings includes schema:ImageObject as the extracted data
|
|
relates to image/logo assets
|
|
class_uri: prov:Entity
|
|
close_mappings:
|
|
- schema:ImageObject
|
|
related_mappings:
|
|
- prov:Derivation
|
|
- schema:Brand
|
|
attributes:
|
|
enrichment_timestamp:
|
|
range: datetime
|
|
description: When logo enrichment was performed
|
|
source_url:
|
|
range: uri
|
|
description: URL of the webpage that was scraped for logos
|
|
extraction_method:
|
|
range: string
|
|
description: Method used to extract logos (crawl4ai, playwright, etc.)
|
|
claims:
|
|
range: LogoClaim
|
|
multivalued: true
|
|
inlined_as_list: true
|
|
description: Individual logo/favicon claims extracted from the page
|
|
summary:
|
|
range: LogoEnrichmentSummary
|
|
description: Summary statistics of logo extraction results
|