Triple

T18046889
Position Surface form Disambiguated ID Type / Status
Subject Lucy Griffiths E431802 entity
Predicate name P16 FINISHED
Object Lucy Griffiths 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: Lucy Griffiths | Statement: [Lucy Griffiths, name, Lucy Griffiths]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lucy Griffiths
Context triple: [Lucy Griffiths, name, Lucy Griffiths]
  • A. Lucy Griffiths chosen
    Lucy Griffiths is an English actress best known for her role as Marian in the BBC television drama "Robin Hood."
  • B. Lucy Tait
    Lucy Tait is the daughter of writer and philosopher Katharine Tait and a member of the extended Russell family lineage.
  • C. Lucy Shepherd
    Lucy Shepherd is a fictional character from the romantic political film "The American President," portrayed as the teenage daughter of the U.S. president.
  • D. Lucy Briers
    Lucy Briers is an English actress known for her work in television, film, and theatre, including her role as Mary Bennet in the 1995 BBC adaptation of "Pride and Prejudice."
  • E. Jaye Griffiths
    Jaye Griffiths is a British actress known for her work in television dramas and science fiction series, including roles in shows like "Doctor Who," "Casualty," and "Silent Witness."
  • 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_69d8b906482481908183315b9ecf9994 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4bff2d3c48190875ffe9c042d3ec0 completed April 19, 2026, 11:43 a.m.
Created at: April 10, 2026, 10:25 a.m.