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

48 lines
2.3 KiB
YAML

id: https://nde.nl/ontology/hc/class/ExtractionMethod
name: ExtractionMethod
title: ExtractionMethod Class - Methods for Data Extraction
prefixes:
linkml: https://w3id.org/linkml/
hc: https://nde.nl/ontology/hc/
schema: http://schema.org/
prov: http://www.w3.org/ns/prov#
nif: http://persistence.uni-leipzig.org/nlp2rdf/ontologies/nif-core#
imports:
- linkml:types
- ../slots/has_label
default_prefix: hc
classes:
ExtractionMethod:
class_uri: prov:SoftwareAgent
description: "A method or technique used to extract data from a source.\n\nExtraction methods define HOW data was obtained, providing\ntransparency and reproducibility for claim provenance.\n\n**Common Extraction Methods**:\n- `xpath_exact_match`: XPath query with exact text match\n- `xpath_fuzzy_match`: XPath query with fuzzy text matching\n- `text_search`: Full-text search within document\n- `css_selector`: CSS selector for element location\n- `json_ld_parse`: Parsing structured JSON-LD data\n- `regex_pattern`: Regular expression pattern matching\n- `nlp_ner`: Named Entity Recognition via NLP\n- `manual_annotation`: Human annotator extraction\n\n**Ontology Mapping Rationale**:\n- class_uri is prov:SoftwareAgent because extraction methods\n are typically software-based agents that perform extraction\n- close_mappings includes nif:Context as NIF models text\n extraction contexts and methods\n\n**MIGRATION NOTE (2026-01-19)**:\nCreated per slot_fixes.yaml revision for claim_extraction_method\n\
slot migration (Rule 53/56).\n"
exact_mappings:
- prov:SoftwareAgent
close_mappings:
- nif:Context
- schema:HowTo
slots:
- has_label
slot_usage:
has_label:
range: Label
inlined: true
required: true
comments:
- 'CREATED 2026-01-19: Per slot_fixes.yaml revision (Rule 53/56)'
- Replaces string-valued claim_extraction_method slot
- Enables structured representation of extraction techniques
examples:
- value:
has_label:
has_label: xpath_exact_match
- value:
has_label:
has_label: nlp_ner
- value:
has_label:
has_label: json_ld_parse
annotations:
specificity_score: 0.1
specificity_rationale: Generic utility class/slot created during migration
custodian_types: "['*']"