Triple

T20841638
Position Surface form Disambiguated ID Type / Status
Subject The Pirate Movie E513115 entity
Predicate castMember P1668 FINISHED
Object Ruth Madoc 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: Ruth Madoc | Statement: [The Pirate Movie, castMember, Ruth Madoc]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ruth Madoc
Context triple: [The Pirate Movie, castMember, Ruth Madoc]
  • A. Ruth Madoc chosen
    Ruth Madoc was a Welsh actress best known for her comedic role as Gladys Pugh in the BBC sitcom "Hi-de-Hi!" and for her extensive work in British television and theatre.
  • B. Sophie Wright
    Sophie Wright is a British chef and food writer known for her cookbooks, television appearances, and work promoting accessible, seasonal cooking.
  • C. Margaret Doherty
    Margaret Doherty is best known as the mother of Kieran Doherty, a prominent Irish republican hunger striker and politician.
  • D. Jane Sheppard
    Jane Sheppard is a character in J.G. Ballard’s novel "Concrete Island," notable for her complex involvement with the stranded protagonist on the derelict traffic island.
  • E. Sarah Greenwood
    Sarah Greenwood is an acclaimed British production designer known for her richly detailed work on major films, including the fantasy world of Barbieland in the 2023 movie "Barbie."
  • 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_69e0b4cf62a88190bbf92351e9e57259 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c34be7a081909c9e98e7f7af7fde completed April 21, 2026, 12:22 a.m.
Created at: April 16, 2026, 12:43 p.m.