Triple

T14235183
Position Surface form Disambiguated ID Type / Status
Subject Race to Witch Mountain E352858 entity
Predicate producer P490 FINISHED
Object Andrew Gunn E583601 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: Andrew Gunn | Statement: [Race to Witch Mountain, producer, Andrew Gunn]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Andrew Gunn
Context triple: [Race to Witch Mountain, producer, Andrew Gunn]
  • A. Andrew Gunn chosen
    Andrew Gunn is an American film producer known for his work on family-oriented and teen-focused movies, including several popular Disney films.
  • B. Gavin Raeburn
    Gavin Raeburn is a British video game developer and studio leader best known as the co-founder and former head of Playground Games, the team behind the Forza Horizon series.
  • C. Mike Caird
    Mike Caird is a Scottish football executive best known for serving as chairman of Arbroath Football Club.
  • D. Kevin Beattie
    Kevin Beattie was an English central defender renowned as one of Ipswich Town’s greatest ever players and a standout talent of 1970s English football.
  • E. Douglas Ross
    Douglas Ross is a television producer best known for creating and producing popular reality TV series.
  • 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_69d8278adc7c8190a9218d69bce3c4e6 completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de62411c888190a154acd56fe3fcaf completed April 14, 2026, 3:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd46794e9c819093312a2c304e554e completed May 8, 2026, 2:12 a.m.
Created at: April 10, 2026, 1:07 a.m.