Triple

T10888284
Position Surface form Disambiguated ID Type / Status
Subject John Dighton E257108 entity
Predicate name P16 FINISHED
Object John Dighton E257108 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: John Dighton | Statement: [John Dighton, name, John Dighton]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: John Dighton
Context triple: [John Dighton, name, John Dighton]
  • A. John Dighton chosen
    John Dighton was a British screenwriter known for his work on classic mid-20th-century films, including co-writing the screenplay for "Roman Holiday."
  • B. John Moultrie
    John Moultrie was an 18th-century British colonial official and planter who served as a leading political figure in British East Florida during the American Revolutionary era.
  • C. Thomas Bartlett
    Thomas Bartlett is an American pianist, producer, and composer known for his work across indie, folk, and experimental music, collaborating with artists such as Sufjan Stevens, The National, and St. Vincent.
  • D. Nathaniel Motte
    Nathaniel Motte is an American musician, producer, and member of the electronic music duo 3OH!3.
  • E. James Widdoes
    James Widdoes is an American actor, director, and television producer best known for directing and producing numerous sitcoms, including extensive work on series like Two and a Half Men and Mom.
  • 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_69d6aa848804819081b2713ca0bedf06 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d75202b7248190adeb5780fc5b9199 completed April 9, 2026, 7:15 a.m.
NED1 Entity disambiguation (via context triple) batch_69e2169ea02c8190addf125ec5adafe8 completed April 17, 2026, 11:16 a.m.
Created at: April 8, 2026, 9:21 p.m.