Triple

T2021199
Position Surface form Disambiguated ID Type / Status
Subject Sarah Hughes E44108 entity
Predicate sibling P363 FINISHED
Object Matt Hughes E213615 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: Matt Hughes | Statement: [Sarah Hughes, sibling, Matt Hughes]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Matt Hughes
Context triple: [Sarah Hughes, sibling, Matt Hughes]
  • A. Matt Hughes chosen
    Matt Hughes is a retired American mixed martial artist widely regarded as one of the greatest welterweights in UFC history, known for his dominant wrestling and multiple championship reigns.
  • B. Kevin Hageman
    Kevin Hageman is an American screenwriter and producer known for his work on animated and family films and television series, including contributions to The Lego Movie franchise.
  • C. Pat Hughes
    Pat Hughes is a longtime American sportscaster best known as the radio play-by-play voice of Major League Baseball’s Chicago Cubs.
  • D. Mark Herron
    Mark Herron was an American actor best known for being the fourth husband of legendary entertainer Judy Garland.
  • E. Matthew Rutler
    Matthew Rutler is an American film production assistant and guitarist best known for his long-term relationship and marriage to singer Christina Aguilera.
  • 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_69a8891201bc8190aca837be6de41579 completed March 4, 2026, 7:33 p.m.
NER Named-entity recognition batch_69abb8ee02dc81908fec9fd8df7a4f40 completed March 7, 2026, 5:34 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae0af60fac8190bc8c8a212a422305 completed March 8, 2026, 11:49 p.m.
Created at: March 4, 2026, 7:38 p.m.