Triple

T17065560
Position Surface form Disambiguated ID Type / Status
Subject Forrest Bondurant E414077 entity
Predicate portrayedBy P1507 FINISHED
Object Tom Hardy E52981 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: Tom Hardy | Statement: [Forrest Bondurant, portrayedBy, Tom Hardy]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tom Hardy
Context triple: [Forrest Bondurant, portrayedBy, Tom Hardy]
  • A. Tom Hardy chosen
    Tom Hardy is an acclaimed English actor known for his intense, transformative performances in films such as Inception, Mad Max: Fury Road, and The Dark Knight Rises.
  • B. Cillian Murphy
    Cillian Murphy is an Irish actor known for his intense, transformative performances in film and television, including roles in "Peaky Blinders," "28 Days Later," and numerous Christopher Nolan movies.
  • C. Dominic Cooper
    Dominic Cooper is an English actor known for his roles in films such as "Mamma Mia!" and "The Devil's Double," as well as the TV series "Preacher."
  • D. Charlie Cavill
    Charlie Cavill is a British public figure best known as the brother of actor Henry Cavill.
  • E. Jonathan Rhys Hill
    Jonathan Rhys Hill is a composer best known for his work on television drama scores, including the series "The Trial of Christine Keeler."
  • 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_69d886cde3d481908d4d01ba88ba7eb7 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3db806de48190a9ce68b40fc77a74 completed April 18, 2026, 7:29 p.m.
NED1 Entity disambiguation (via context triple) batch_6a01234e9a94819094618ba43b7d22b4 completed May 11, 2026, 12:31 a.m.
Created at: April 10, 2026, 5:34 a.m.