Triple

T4481234
Position Surface form Disambiguated ID Type / Status
Subject Frederick Dent Grant E100138 entity
Predicate familyName P18 FINISHED
Object Grant E182443 NE FINISHED

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: Grant | Statement: [Frederick Dent Grant, familyName, Grant]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Grant
Context triple: [Frederick Dent Grant, familyName, Grant]
  • A. Grant chosen
    Grant is a masculine given name of English origin that is commonly used in the United States and other English-speaking countries.
  • B. Grant
    Grant is a publishing company best known for releasing special and limited editions of Stephen King’s works, including volumes in The Dark Tower series.
  • C. Jones
    Jones is a common English-language surname borne by numerous notable individuals across fields such as entertainment, sports, politics, and science.
  • D. Red Grant
    Red Grant is a ruthless, psychopathic assassin and primary antagonist in the James Bond franchise, most prominently appearing as SPECTRE’s top killer in the film and novel "From Russia, with Love."
  • E. Grantley
    Grantley is the given name of Grantley Herbert Adams, a prominent Barbadian and Caribbean political leader and the first Premier of Barbados.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69b34553cbe48190afa8ac1cac285b86 completed March 12, 2026, 10:59 p.m.
NER Named-entity recognition batch_69b356dddd488190bd5dedd3c0e77247 completed March 13, 2026, 12:14 a.m.
NED1 Entity disambiguation (via context triple) batch_69b6377c694881909428b5cffb405c8d completed March 15, 2026, 4:37 a.m.
Created at: March 12, 2026, 11:36 p.m.