Triple

T17693166
Position Surface form Disambiguated ID Type / Status
Subject Karl Kennedy E441085 entity
Predicate relative P37 FINISHED
Object Malcolm Kennedy 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: Malcolm Kennedy | Statement: [Karl Kennedy, relative, Malcolm Kennedy]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Malcolm Kennedy
Context triple: [Karl Kennedy, relative, Malcolm Kennedy]
  • A. Malcolm Kennedy chosen
    Malcolm Kennedy is a fictional character from the Australian soap opera "Neighbours," known as one of Karl and Susan Kennedy’s children.
  • B. Karl Kennedy
    Karl Kennedy is a long-running fictional doctor and central character on the Australian soap opera "Neighbours," known for his complex family and relationship storylines.
  • C. Malcolm Cameron
    Malcolm Cameron is a notable individual who shares the surname Cameron and is recognized for his prominence in public or professional life.
  • D. Lord Kennedy
    Lord Kennedy is a Scottish noble title historically associated with the leadership of Clan Kennedy and the Ayrshire peerage.
  • E. Peter MacGregor-Scott
    Peter MacGregor-Scott was a British film and television producer best known for his work on major Hollywood action and franchise films in the 1980s and 1990s.
  • 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_69d8b9e940b081908b862bb0e6e89b0d completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e47153a5c8819095c36fd414167fb1 completed April 19, 2026, 6:08 a.m.
Created at: April 10, 2026, 10:03 a.m.