Triple

T17311505
Position Surface form Disambiguated ID Type / Status
Subject Lucy Gaskell E420308 entity
Predicate spouse P13 FINISHED
Object Mark Bonnar E1158137 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: Mark Bonnar | Statement: [Lucy Gaskell, spouse, Mark Bonnar]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mark Bonnar
Context triple: [Lucy Gaskell, spouse, Mark Bonnar]
  • A. Mark Bonnar chosen
    Mark Bonnar is a Scottish actor known for his versatile roles in television dramas such as "Line of Duty," "Catastrophe," and "Unforgotten."
  • B. Glen Matlock
    Glen Matlock is an English bassist and songwriter best known as a founding member of the pioneering punk rock band the Sex Pistols.
  • C. Malcolm Loughead
    Malcolm Loughead was an early American aviation pioneer and co-founder of the company that evolved into the major aerospace manufacturer Lockheed.
  • D. Sebastian Bach
    Sebastian Bach is a Canadian heavy metal singer best known as the former frontman of the band Skid Row.
  • E. Tony MacAlpine
    Tony MacAlpine is an American guitarist and keyboardist known for his virtuosic neoclassical metal and instrumental rock work, as well as collaborations with prominent guitarists and fusion projects.
  • 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_69d889d22b848190a4663d0b8f8f76e7 completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e439993bac8190a72f6af529bd7cce completed April 19, 2026, 2:10 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0180e5043081908f31c2434e9b9647 completed May 11, 2026, 7:10 a.m.
Created at: April 10, 2026, 5:43 a.m.