Triple

T15768807
Position Surface form Disambiguated ID Type / Status
Subject Twister E382294 entity
Predicate starring P1507 FINISHED
Object Jeremy Davies NE NERFINISHED

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: Jeremy Davies | Statement: [Twister, starring, Jeremy Davies]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jeremy Davies
Context triple: [Twister, starring, Jeremy Davies]
  • A. Jeremy Davies chosen
    Jeremy Davies is an American actor best known for his intense, often eccentric performances in films and television series such as "Saving Private Ryan," "Spanking the Monkey," and "Justified."
  • B. Nigel Havers
    Nigel Havers is an English actor best known for his suave, upper-class roles in film and television, including his acclaimed performance in the Oscar-winning drama "Chariots of Fire."
  • C. William John Postlethwaite
    William John Postlethwaite is a British actor known for his work in film, television, and theatre, and as the son of acclaimed character actor Pete Postlethwaite.
  • D. Clive Standen
    Clive Standen is a British actor best known for his roles in historical and action television series such as Vikings and Taken.
  • E. Rupert Penry-Jones
    Rupert Penry-Jones is a British actor known for his roles in television dramas such as "Spooks" and "Silk," as well as various film and stage productions.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d86da09a10819082fe9797b23e4664 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e051951bac8190a7d45f3612c6de72 completed April 16, 2026, 3:03 a.m.
Created at: April 10, 2026, 4:47 a.m.