Triple

T20155447
Position Surface form Disambiguated ID Type / Status
Subject Bill Hunter E491550 entity
Predicate spouse P13 FINISHED
Object Robyn Nevin 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: Robyn Nevin | Statement: [Bill Hunter, spouse, Robyn Nevin]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Robyn Nevin
Context triple: [Bill Hunter, spouse, Robyn Nevin]
  • A. Robyn Nevin chosen
    Robyn Nevin is a prominent Australian actress and theatre director known for her extensive work on stage, film, and television, as well as her leadership roles in major Australian theatre companies.
  • B. Tania Tapsell
    Tania Tapsell is a New Zealand politician and local government leader known for serving as the mayor of Rotorua and for her prominence as a young Māori woman in public office.
  • C. Claire Jackman
    Claire Jackman is a fictional character portrayed by actress Gina Bellman, known from her work in British television and film.
  • D. Jennifer Hennessy
    Jennifer Hennessy is a British actress known for her work in television dramas and comedies, including appearances in series such as Doctor Who and The Office.
  • E. Kerry Bishé
    Kerry Bishé is a New Zealand–born American actress best known for her roles in the film "Argo" and the television series "Halt and Catch Fire."
  • 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_69da6265f8f0819080b29c752a574088 completed April 11, 2026, 3:01 p.m.
NER Named-entity recognition batch_69e667df7ac081908816d2d29e7c6513 completed April 20, 2026, 5:52 p.m.
Created at: April 11, 2026, 11:34 p.m.