Triple

T17990749
Position Surface form Disambiguated ID Type / Status
Subject Child 44 E430362 entity
Predicate filmAdaptationStar P795 FINISHED
Object Tom Hardy 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: Tom Hardy | Statement: [Child 44, filmAdaptationStar, Tom Hardy]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tom Hardy
Context triple: [Child 44, filmAdaptationStar, 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 (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_69d8b90364248190a37381adea932f42 completed April 10, 2026, 8:46 a.m.
NER Named-entity recognition batch_69e4b29f127c81908b0c4cb3787e002c completed April 19, 2026, 10:46 a.m.
Created at: April 10, 2026, 10:23 a.m.