Triple

T11363905
Position Surface form Disambiguated ID Type / Status
Subject Will Knightley E269153 entity
Predicate spouse P13 FINISHED
Object Sharman Macdonald E269152 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: Sharman Macdonald | Statement: [Will Knightley, spouse, Sharman Macdonald]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sharman Macdonald
Context triple: [Will Knightley, spouse, Sharman Macdonald]
  • A. Sharman Macdonald chosen
    Sharman Macdonald is a Scottish playwright, screenwriter, and former actress known for works such as the play "When I Was a Girl I Used to Scream and Shout."
  • B. Jo MacLean
    Jo MacLean is a Scottish music promoter best known for co-founding and helping develop the Tiree Music Festival, a popular island music event in the Hebrides.
  • C. Jamie Scott
    Jamie Scott is a British singer-songwriter and producer known for his work with artists like One Direction and for co-writing numerous contemporary pop hits.
  • D. Darin McFadyen
    Darin McFadyen is a New Zealand-born DJ and producer best known for his breakbeat and electronic music work under the stage name Freq Nasty.
  • E. Jimmy Yuill
    Jimmy Yuill is a Scottish actor known for his work in film, television, and theatre, including roles in several Shakespearean adaptations.
  • 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_69e58bb3bd648190affa7ee85027c958 completed April 20, 2026, 2:13 a.m.
Created at: April 8, 2026, 9:33 p.m.