Triple

T14275318
Position Surface form Disambiguated ID Type / Status
Subject Claudia Winkleman E353900 entity
Predicate presenterOf P83 FINISHED
Object BBC Radio 2 shows E77718 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: BBC Radio 2 shows | Statement: [Claudia Winkleman, presenterOf, BBC Radio 2 shows]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: BBC Radio 2 shows
Context triple: [Claudia Winkleman, presenterOf, BBC Radio 2 shows]
  • A. BBC Radio 2 chosen
    BBC Radio 2 is a major UK national radio station known for its broad mix of popular music, entertainment, and speech programming aimed primarily at adult listeners.
  • B. Radio 2UE
    Radio 2UE is a long-running Sydney-based commercial talk radio station known for its news, talkback, and sports programming.
  • C. BBC Radio and Music
    BBC Radio and Music is the BBC division responsible for overseeing the corporation’s UK radio stations and music-related content and strategy.
  • D. CBC Radio 2
    CBC Radio 2 is a Canadian public radio network operated by the Canadian Broadcasting Corporation, known for its focus on music and cultural programming.
  • E. BBC Radio 7
    BBC Radio 7 was a British digital radio station specializing in comedy, drama, and entertainment programming from the BBC archives.
  • 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_69d8278d25148190abf1a8c8f5f533ad completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de6582f5308190969f4cfd724d9139 completed April 14, 2026, 4:04 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd326d35808190bbf3f6bbc50554f4 completed May 8, 2026, 12:46 a.m.
Created at: April 10, 2026, 1:10 a.m.