Triple

T20807889
Position Surface form Disambiguated ID Type / Status
Subject The Buccaneer (1958 film) E512211 entity
Predicate hasCastMember P2308 FINISHED
Object Claire Kelly
Claire Kelly was an American actress and model active in the 1950s and 1960s, known for her supporting roles in Hollywood films and television.
E1467853 NE FINISHED

How this triple was built (4 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: Claire Kelly | Statement: [The Buccaneer (1958 film), hasCastMember, Claire Kelly]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Claire Kelly
Context triple: [The Buccaneer (1958 film), hasCastMember, Claire Kelly]
  • A. Claire McCarthy
    Claire McCarthy is an Australian filmmaker and screenwriter known for directing visually rich, character-driven dramas such as the 2018 adaptation of "Ophelia."
  • B. Madeleine Kelly
    Madeleine Kelly is one of the children of renowned Australian singer-songwriter Paul Kelly.
  • C. Claire Lydon
    Claire Lydon was the wife of American novelist Clifford Irving, who gained notoriety for his fraudulent "autobiography" of Howard Hughes.
  • D. Christine Kelly
    Christine Kelly is the wife of American filmmaker Abel Ferrara, known for her association with his life and career.
  • E. Claire Craig
    Claire Craig is a British academic and former civil servant who serves as the Provost (head) of The Queen’s College, University of Oxford.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Claire Kelly
Triple: [The Buccaneer (1958 film), hasCastMember, Claire Kelly]
Generated description
Claire Kelly was an American actress and model active in the 1950s and 1960s, known for her supporting roles in Hollywood films and television.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Claire Kelly
Target entity description: Claire Kelly was an American actress and model active in the 1950s and 1960s, known for her supporting roles in Hollywood films and television.
  • A. Claire McCarthy
    Claire McCarthy is an Australian filmmaker and screenwriter known for directing visually rich, character-driven dramas such as the 2018 adaptation of "Ophelia."
  • B. Madeleine Kelly
    Madeleine Kelly is one of the children of renowned Australian singer-songwriter Paul Kelly.
  • C. Claire Lydon
    Claire Lydon was the wife of American novelist Clifford Irving, who gained notoriety for his fraudulent "autobiography" of Howard Hughes.
  • D. Christine Kelly
    Christine Kelly is the wife of American filmmaker Abel Ferrara, known for her association with his life and career.
  • E. Claire Craig
    Claire Craig is a British academic and former civil servant who serves as the Provost (head) of The Queen’s College, University of Oxford.
  • F. None of above. chosen

Provenance (5 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_69e0b4cc69f481908e98751e697b9df4 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c2d0a2a081908fb0e3d890e87aaf completed April 21, 2026, 12:20 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0965cd0b548190be47c7896c754c8d completed May 17, 2026, 6:53 a.m.
NEDg Description generation batch_6a09670987f0819086b021581db69c85 completed May 17, 2026, 6:58 a.m.
NED2 Entity disambiguation (via description) batch_6a0967cefab08190b01e2c897f081105 completed May 17, 2026, 7:01 a.m.
Created at: April 16, 2026, 12:40 p.m.