Triple

T8302556
Position Surface form Disambiguated ID Type / Status
Subject Denny Vrandečić E194381 entity
Predicate notableWork P4 FINISHED
Object Semantic MediaWiki E473153 NE FINISHED

How this triple was built (2 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Semantic MediaWiki | Statement: [Denny Vrandečić, notableWork, Semantic MediaWiki]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Semantic MediaWiki
Context triple: [Denny Vrandečić, notableWork, Semantic MediaWiki]
  • A. Semantic MediaWiki chosen
    Semantic MediaWiki is an extension to the MediaWiki platform that adds semantic annotation and querying capabilities, turning wiki content into a structured, queryable knowledge base.
  • B. Wikibase
    Wikibase is a free, open-source software suite developed by Wikimedia for storing, managing, and querying structured, linked data.
  • C. Semantic Web
    The Semantic Web is an extension of the current web in which information is given well-defined meaning through standards like RDF and OWL, enabling machines to understand, share, and reason about data across different systems.
  • D. Wikidata
    Wikidata is a collaboratively edited, multilingual knowledge base that provides structured data to support Wikipedia and other Wikimedia projects.
  • E. Microdata
    Microdata is an HTML-based specification for embedding machine-readable metadata within web pages to improve data interoperability and search engine understanding.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69ca82e613e88190bf8139669bbd0d53 completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cb7e8a45348190a7895b33abcb64c9 completed March 31, 2026, 7:58 a.m.
NED1 Entity disambiguation (via context triple) batch_69cd68c2a14c81908388ecdd22315390 completed April 1, 2026, 6:49 p.m.
Created at: March 30, 2026, 5:53 p.m.