Triple

T619852
Position Surface form Disambiguated ID Type / Status
Subject BBC E14486 entity
Predicate notableProgram P4 FINISHED
Object BBC News at Ten E71374 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 News at Ten | Statement: [BBC, notableProgram, BBC News at Ten]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: BBC News at Ten
Context triple: [BBC, notableProgram, BBC News at Ten]
  • A. BBC News at Ten chosen
    BBC News at Ten is the BBC’s flagship late-evening television news bulletin, providing national and international news coverage on weekdays.
  • B. BBC News at Six
    BBC News at Six is a flagship early evening television news bulletin on BBC One, providing national and international news coverage to UK audiences.
  • C. BBC Breakfast
    BBC Breakfast is a long-running British morning television news and magazine programme featuring news, interviews, weather, and lifestyle segments.
  • D. BBC One
    BBC One is the BBC’s flagship television channel in the United Kingdom, known for broadcasting a wide range of popular news, drama, comedy, and entertainment programs.
  • E. Sky News
    Sky News is a British 24-hour television news channel and digital news service known for live breaking news coverage in the UK and internationally.
  • 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_69a4934b17c881909ace8270e8ddd202 completed March 1, 2026, 7:28 p.m.
NER Named-entity recognition batch_69a49e270b448190beb677670443b5b6 completed March 1, 2026, 8:14 p.m.
NED1 Entity disambiguation (via context triple) batch_69a55a79a0488190a9d22229ea97e5ec completed March 2, 2026, 9:38 a.m.
Created at: March 1, 2026, 7:35 p.m.