glam/schemas/20251121/linkml/modules/classes/DataSource.yaml

119 lines
4 KiB
YAML

id: https://nde.nl/ontology/hc/class/DataSource
name: data_source_class
title: DataSource Class
description: >-
Represents a source of data for enrichment or information gathering.
Used to track where data came from, including messaging platforms,
APIs, web scraping, databases, and other data sources.
prefixes:
linkml: https://w3id.org/linkml/
hc: https://nde.nl/ontology/hc/
prov: http://www.w3.org/ns/prov#
dcterms: http://purl.org/dc/terms/
schema: http://schema.org/
imports:
- linkml:types
- ../slots/has_or_had_label
- ../slots/has_or_had_description
- ../slots/has_or_had_code
- ../slots/source_url
default_prefix: hc
classes:
DataSource:
class_uri: prov:Entity
description: >-
A source of data used for enrichment or information gathering.
**Common Source Types**:
| Type | Short Code | Description |
|------|------------|-------------|
| WhatsApp | WHATSAPP | WhatsApp messaging platform |
| LinkedIn | LINKEDIN | LinkedIn social network |
| Web Scrape | WEB_SCRAPE | Website scraping |
| API | API | External API |
| Database | DATABASE | Database query |
| Manual | MANUAL | Manual entry |
| Wikidata | WIKIDATA | Wikidata knowledge base |
| Google Maps | GOOGLE_MAPS | Google Maps API |
**PROV-O Alignment**: Maps to prov:Entity as the source entity
from which data was derived.
exact_mappings:
- prov:Entity
close_mappings:
- dcterms:source
- schema:CreativeWork
slots:
- has_or_had_label
- has_or_had_code
- has_or_had_description
- source_url
slot_usage:
has_or_had_label:
description: Human-readable name for the data source.
range: string
required: true
examples:
- value: "WhatsApp"
description: WhatsApp messaging platform
- value: "LinkedIn Profile"
description: LinkedIn social network
has_or_had_code:
description: >-
Short code identifier for the data source type.
Examples: WHATSAPP, LINKEDIN, WEB_SCRAPE, API, DATABASE, MANUAL
range: string
required: true
pattern: "^[A-Z][A-Z0-9_]*$"
examples:
- value: "WHATSAPP"
description: WhatsApp platform
- value: "LINKEDIN"
description: LinkedIn platform
- value: "WEB_SCRAPE"
description: Website scraping
has_or_had_description:
description: Detailed description of the data source and how it was used.
range: string
required: false
examples:
- value: "Profile information extracted from WhatsApp message exchange"
description: WhatsApp source description
source_url:
description: URL or identifier for the specific source location.
range: uriorcurie
required: false
examples:
- value: "https://linkedin.com/in/example-profile"
description: LinkedIn profile URL
annotations:
specificity_score: 0.35
specificity_rationale: >-
Data sources are broadly applicable across all enrichment contexts.
custodian_types: '["*"]'
custodian_types_rationale: >-
Data sources apply universally to all custodian types.
examples:
- value:
has_or_had_label: "WhatsApp"
has_or_had_code: "WHATSAPP"
has_or_had_description: "Information gathered via WhatsApp conversation"
description: WhatsApp data source
- value:
has_or_had_label: "LinkedIn Profile"
has_or_had_code: "LINKEDIN"
has_or_had_description: "Profile information from LinkedIn"
source_url: "https://linkedin.com/in/example-profile"
description: LinkedIn data source with URL
- value:
has_or_had_label: "Wikidata"
has_or_had_code: "WIKIDATA"
has_or_had_description: "Entity data from Wikidata SPARQL query"
source_url: "https://www.wikidata.org/wiki/Q12345"
description: Wikidata data source