Triple

T15486853
Position Surface form Disambiguated ID Type / Status
Subject Project Blue Book E377069 entity
Predicate executiveProducer P7225 FINISHED
Object David O’Leary E1160736 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: David O’Leary | Statement: [Project Blue Book, executiveProducer, David O’Leary]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: David O’Leary
Context triple: [Project Blue Book, executiveProducer, David O’Leary]
  • A. David O’Leary chosen
    David O’Leary is a television writer and producer best known for creating the historical sci-fi drama series "Project Blue Book."
  • B. Bill Gartley
    Bill Gartley is the ruthless and sadistic owner of a laundry factory in the horror film "The Mangler," where a possessed industrial machine terrorizes workers.
  • C. Nigel Bowen
    Nigel Bowen is a New Zealand local-body politician who serves as the mayor of the Timaru District in the South Island.
  • D. Bill Curbishley
    Bill Curbishley is a British music and film producer and band manager best known for his long-time work with rock bands like The Who and Judas Priest.
  • E. Dave Whelan
    Dave Whelan is an English businessman and former professional footballer best known for transforming Wigan Athletic into a Premier League club and leading them to major domestic success.
  • 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_69d85cd21dcc81908646251b1c26ea00 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e03f8f71a08190a440ff19dcc65312 completed April 16, 2026, 1:46 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff454ac84c8190b1979e6caca3ee66 completed May 9, 2026, 2:31 p.m.
Created at: April 10, 2026, 3:47 a.m.