Triple

T17531077
Position Surface form Disambiguated ID Type / Status
Subject Yamada E426932 entity
Predicate romanizationSystem P6517 FINISHED
Object Hepburn 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: Hepburn | Statement: [Yamada, romanizationSystem, Hepburn]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hepburn
Context triple: [Yamada, romanizationSystem, Hepburn]
  • A. Hepburn chosen
    Hepburn is a widely used system for transcribing Japanese sounds into the Latin alphabet, originally developed by American missionary James Curtis Hepburn.
  • B. Hepburn
    Hepburn is a Scottish noble family name most famously associated with James Hepburn, 4th Earl of Bothwell, the third husband of Mary, Queen of Scots.
  • C. Hepburn Ferrer
    Hepburn Ferrer is the family name of Sean Hepburn Ferrer, the son of iconic actress Audrey Hepburn and actor Mel Ferrer.
  • D. Tracy and Hepburn
    "Tracy and Hepburn" is Garson Kanin’s acclaimed 1971 dual biography chronicling the professional and romantic partnership of Hollywood legends Spencer Tracy and Katharine Hepburn.
  • E. Adele H. Hepburn
    Adele H. Hepburn was the wife of prominent American politician William Peters Hepburn, associated with his career and life in late 19th- and early 20th-century Iowa.
  • 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_69d889de677081909b22d2657b1f0292 completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e453688950819098162d853cd2674e completed April 19, 2026, 4 a.m.
Created at: April 10, 2026, 5:49 a.m.