Triple

T11363870
Position Surface form Disambiguated ID Type / Status
Subject Sharman Macdonald E269152 entity
Predicate spouse P13 FINISHED
Object Will Knightley E269153 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: Will Knightley | Statement: [Sharman Macdonald, spouse, Will Knightley]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Will Knightley
Context triple: [Sharman Macdonald, spouse, Will Knightley]
  • A. Will Knightley chosen
    Will Knightley is a British stage and television actor best known as the father of acclaimed actress Keira Knightley.
  • B. Ben Barnes
    Ben Barnes is an English actor best known for his roles in films like "The Chronicles of Narnia" series and "Dorian Gray," as well as TV shows such as "Westworld" and "Shadow and Bone."
  • C. Dominic Keating
    Dominic Keating is a British actor best known for playing Lieutenant Malcolm Reed on the science fiction television series Star Trek: Enterprise.
  • D. Jonathan Rhys Meyers
    Jonathan Rhys Meyers is an Irish actor best known for his roles in films like "Match Point" and the TV series "The Tudors," in which he portrayed King Henry VIII.
  • E. Matthew Goode
    Matthew Goode is an English actor known for his roles in films such as "Match Point," "The Imitation Game," and "Stoker," as well as TV series like "Downton Abbey" and "The Good Wife."
  • 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_69d6aacbe18081909e5fadb50082dd96 completed April 8, 2026, 7:21 p.m.
NER Named-entity recognition batch_69d7ea4589908190948a8225768e1eec completed April 9, 2026, 6:04 p.m.
NED1 Entity disambiguation (via context triple) batch_69e5565df5508190aeda7d064bceb157 completed April 19, 2026, 10:25 p.m.
Created at: April 8, 2026, 9:33 p.m.