Triple

T3536953
Position Surface form Disambiguated ID Type / Status
Subject Dominic Lewis E74793 entity
Predicate name P16 FINISHED
Object Dominic Lewis E74793 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: Dominic Lewis | Statement: [Dominic Lewis, name, Dominic Lewis]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dominic Lewis
Context triple: [Dominic Lewis, name, Dominic Lewis]
  • A. Dominic Lewis chosen
    Dominic Lewis is a British-born film and television composer known for scoring a variety of Hollywood projects across action, animation, and comedy.
  • B. Dominic Holland
    Dominic Holland is a British comedian, author, and broadcaster, best known for his stand-up work, radio shows, and writing, as well as being the father of actor Tom Holland.
  • C. Kai Owen
    Kai Owen is a Welsh actor best known for his role as Rhys Williams in the BBC science fiction series Torchwood.
  • D. Ryan Bamford
    Ryan Bamford is a collegiate athletics administrator best known for serving as the athletic director at the University of Massachusetts Amherst.
  • E. Robbie Cowling
    Robbie Cowling is a British businessman best known as the long-serving owner and chairman of Colchester United Football Club.
  • 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_69ad85d274cc8190ab59c97298a1cfbf completed March 8, 2026, 2:21 p.m.
NER Named-entity recognition batch_69adbcc7b92481908d2d99948780f4d0 completed March 8, 2026, 6:15 p.m.
NED1 Entity disambiguation (via context triple) batch_69b38bd237e881909df210a42346b572 completed March 13, 2026, 4 a.m.
Created at: March 8, 2026, 3:20 p.m.