Triple

T7656633
Position Surface form Disambiguated ID Type / Status
Subject Charlotte Riley E173400 entity
Predicate spouse P13 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: [Charlotte Riley, spouse, Tom Hardy]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tom Hardy
Context triple: [Charlotte Riley, spouse, 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. Robert Pattinson
    Robert Pattinson is an English actor best known for his roles as vampire Edward Cullen in the Twilight film series and as the title character in the 2022 superhero film "The Batman."
  • 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_69c69955517c819085bc715b96d304d2 completed March 27, 2026, 2:51 p.m.
NER Named-entity recognition batch_69c7018fcbb48190a479f2effd939a8e completed March 27, 2026, 10:15 p.m.
NED1 Entity disambiguation (via context triple) batch_69c8a21dd3088190bb026de65970a14b completed March 29, 2026, 3:53 a.m.
Created at: March 27, 2026, 3:59 p.m.