Triple

T14853666
Position Surface form Disambiguated ID Type / Status
Subject Blow E349295 entity
Predicate starring P1507 FINISHED
Object Rachel Griffiths E449396 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: Rachel Griffiths | Statement: [Blow, starring, Rachel Griffiths]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Rachel Griffiths
Context triple: [Blow, starring, Rachel Griffiths]
  • A. Rachel Griffiths chosen
    Rachel Griffiths is an Australian actress known for her acclaimed film and television work, including prominent roles in projects like "Muriel's Wedding," "Hilary and Jackie," and the HBO drama "Six Feet Under."
  • B. Claire Jackman
    Claire Jackman is a fictional character portrayed by actress Gina Bellman, known from her work in British television and film.
  • C. Ruth Grant
    Ruth Grant is the daughter of British thriller novelist Lee Child, known for his Jack Reacher series.
  • D. Suzanne Mackie
    Suzanne Mackie is a British television and film producer known for her work on acclaimed projects such as "The Crown" and other high-profile UK dramas.
  • E. Frances Kirwan
    Frances Kirwan is a prominent British mathematician known for her influential work in algebraic and symplectic geometry and for serving as the first female Savilian Professor of Geometry at the University of Oxford.
  • 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_69d822ed7e1881909b90fca143ad7e34 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69ded44318f0819080b6c599f2d3474f completed April 14, 2026, 11:56 p.m.
NED1 Entity disambiguation (via context triple) batch_69ff9976bc888190a050c2502d1f8e81 completed May 9, 2026, 8:30 p.m.
Created at: April 10, 2026, 1:54 a.m.