Triple

T22442742
Position Surface form Disambiguated ID Type / Status
Subject Thomas Stamford Raffles E554794 entity
Predicate familyName P18 FINISHED
Object Raffles 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: Raffles | Statement: [Thomas Stamford Raffles, familyName, Raffles]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Raffles
Context triple: [Thomas Stamford Raffles, familyName, Raffles]
  • A. Raffles chosen
    Raffles is a surname most famously associated with Sir Thomas Stamford Raffles, the British statesman and founder of modern Singapore.
  • B. Raffles
    Raffles is a 1930 American pre-Code crime drama film, based on the gentleman thief A.J. Raffles, that blends romance and suspense in a story of high-society burglary.
  • C. The Madras House
    The Madras House is a 1910 play by Harley Granville Barker that critiques Edwardian English society and its attitudes toward commerce, marriage, and sexuality.
  • D. City of Orient
    The City of Orient is a small incorporated municipality in Adair County, Iowa, known for its rural Midwestern character and local community governance.
  • E. The Beresford
    The Beresford is a landmark luxury cooperative apartment building in New York City, renowned for its distinctive three-towered design overlooking Central Park.
  • 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_69e11e5010e48190ae1e9c9db9697637 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15ae40f9081908674015beb33f74e completed April 29, 2026, 1:12 a.m.
Created at: April 16, 2026, 8:47 p.m.