Triple

T22496834
Position Surface form Disambiguated ID Type / Status
Subject Matthew E556162 entity
Predicate hasVariantSpelling P457 FINISHED
Object Mathew 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: Mathew | Statement: [Matthew, hasVariantSpelling, Mathew]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mathew
Context triple: [Matthew, hasVariantSpelling, Mathew]
  • A. Mathew chosen
    Mathew is the given name of Mathew Knowles, the American music executive best known as Beyoncé’s father and former manager.
  • B. John Matthew Matthan
    John Matthew Matthan is an Indian film director best known for helming the acclaimed 1999 Hindi crime drama "Sarfarosh."
  • C. Russ Matthews
    Russ Matthews is a fictional character best known as one of Iris Carrington’s significant romantic partners in the long-running soap opera "Another World."
  • D. Daniel Matthews
    Daniel Matthews is a fictional character in the Saw horror film franchise, notably appearing as one of Jigsaw’s trapped victims in Saw II.
  • E. Matthew Nathan
    Matthew Nathan was a British Army officer and colonial administrator who served as Governor of Hong Kong in the early 20th century.
  • 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_69e11e5445bc8190b6a9481926db3355 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15cb2644c819094864bd88bcebcbd completed April 29, 2026, 1:19 a.m.
Created at: April 16, 2026, 8:50 p.m.