Triple

T20294679
Position Surface form Disambiguated ID Type / Status
Subject The Mouse That Roared E510115 entity
Predicate castMember P1668 FINISHED
Object Peter Sellers 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: Peter Sellers | Statement: [The Mouse That Roared, castMember, Peter Sellers]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Peter Sellers
Context triple: [The Mouse That Roared, castMember, Peter Sellers]
  • A. Peter Sellers chosen
    Peter Sellers was a celebrated British comic actor best known for his versatile character work in films such as the Pink Panther series and Dr. Strangelove.
  • B. Peter Ustinov
    Peter Ustinov was a British actor, writer, and director renowned for his wit, versatility, and memorable character roles in film and television.
  • C. Hugh Shearer
    Hugh Shearer was a Jamaican politician, trade unionist, and the third Prime Minister of Jamaica, serving from 1967 to 1972.
  • D. Ian Lithgow
    Ian Lithgow is an American actor and psychotherapist best known for his recurring role as Leon on the sitcom "3rd Rock from the Sun."
  • E. Terry-Thomas
    Terry-Thomas was a distinctive English comic actor known for his gap-toothed grin and portrayals of upper-class cads and bounders in mid-20th-century film and television.
  • 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_69e0b4c652388190b782cad965e5a098 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6770714c4819080e3256325747ebf completed April 20, 2026, 6:57 p.m.
Created at: April 16, 2026, 11:13 a.m.