Triple

T17693161
Position Surface form Disambiguated ID Type / Status
Subject Karl Kennedy E441085 entity
Predicate spouse P13 FINISHED
Object Susan 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: Susan Kennedy | Statement: [Karl Kennedy, spouse, Susan Kennedy]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Susan Kennedy
Context triple: [Karl Kennedy, spouse, Susan Kennedy]
  • A. Susan Kennedy chosen
    Susan Kennedy is a long-running, central character on the Australian soap opera "Neighbours," known for her role as a compassionate school principal and matriarch of the Kennedy family.
  • B. Maria Doyle Kennedy
    Maria Doyle Kennedy is an Irish actress and singer best known internationally for her acclaimed role as Queen Catherine of Aragon in the historical drama series "The Tudors."
  • C. Janet Kennedy
    Janet Kennedy was a prominent Scottish noblewoman and mistress of King James IV of Scotland, noted for her influential connections within the Scottish court.
  • D. Kerry Kennedy
    Kerry Kennedy is an American human rights activist, lawyer, and author, and a daughter of Robert F. Kennedy.
  • E. Emma Kennedy
    Emma Kennedy is a British actress, comedian, and writer known for her work in radio, television, and books, including appearances on BBC Radio 4 comedy programmes.
  • 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.