Triple

T15059345
Position Surface form Disambiguated ID Type / Status
Subject Craig Charles E379582 entity
Predicate employer P7 FINISHED
Object BBC Radio 2 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 | Statement: [Craig Charles, employer, BBC Radio 2]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: BBC Radio 2
Context triple: [Craig Charles, employer, BBC Radio 2]
  • 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 1
    BBC Radio 1 is a major UK national radio station focused on contemporary popular music and youth-oriented programming.
  • 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. Radio 3
    Radio 3 is a Spanish public radio station known for its focus on alternative music, culture, and the arts, and is part of the RTVE broadcasting group.
  • 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_69d85cd64d108190853797a95c11cc45 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69dedee50afc8190bf7b0f4bbe8c60a3 completed April 15, 2026, 12:42 a.m.
NED1 Entity disambiguation (via context triple) batch_69febfdc8f64819083c7e3510e671b9a completed May 9, 2026, 5:02 a.m.
Created at: April 10, 2026, 3:01 a.m.