Triple

T21721644
Position Surface form Disambiguated ID Type / Status
Subject May Grant E536170 entity
Predicate hasBrother P363 FINISHED
Object Harry Grant 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: Harry Grant | Statement: [May Grant, hasBrother, Harry Grant]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Harry Grant
Context triple: [May Grant, hasBrother, Harry Grant]
  • A. Harry Grant chosen
    Harry Grant is a relatively obscure figure primarily known in relation to his daughter, Athena Grant, rather than for widely recognized independent achievements.
  • B. Arthur Grant
    Arthur Grant was a British cinematographer best known for his work on numerous Hammer Films productions in the mid-20th century.
  • C. Robert Grant
    Robert Grant is the harried but good-hearted hotel manager and central human protagonist in the family comedy film "Dunston Checks In."
  • D. Gavin Douglas
    Gavin Douglas was a prominent early 16th-century Scottish poet and bishop, best known for his Middle Scots translation of Virgil's Aeneid, the Eneados.
  • E. Keith Grant
    Keith Grant was a renowned British recording engineer celebrated for his influential work at London’s Olympic Studios with many major rock and pop artists of the 1960s and 1970s.
  • 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_69e0c46c6dd88190a595375fa6ebd701 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69efd96f1fbc8190a202f834aec1a319 completed April 27, 2026, 9:47 p.m.
Created at: April 16, 2026, 6:47 p.m.