Triple

T20350191
Position Surface form Disambiguated ID Type / Status
Subject Street Fighter II E495984 entity
Predicate bossCharacter P98692 FINISHED
Object M. Bison 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: M. Bison | Statement: [Street Fighter II, bossCharacter, M. Bison]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: M. Bison
Context triple: [Street Fighter II, bossCharacter, M. Bison]
  • A. M. Bison chosen
    M. Bison is the main villain of the Street Fighter series, a ruthless dictator and powerful psycho-powered fighter who leads the criminal organization Shadaloo.
  • B. Sagat
    Sagat is a towering Muay Thai fighter and iconic antagonist from the Street Fighter series, known for his scarred chest, powerful Tiger attacks, and rivalry with Ryu.
  • C. Terry Silver
    Terry Silver is a manipulative and wealthy villain in The Karate Kid franchise, known for orchestrating schemes against Daniel LaRusso and supporting the Cobra Kai dojo.
  • D. Gouken
    Gouken is a legendary martial arts master from the Street Fighter series, best known for training Ryu and Ken in the Ansatsuken fighting style.
  • E. Junzaburo Ban
    Junzaburo Ban was a Japanese actor known for his roles in mid-20th-century cinema, including Akira Kurosawa’s film "Dodes'ka-den."
  • 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_69e0b4a3320881909495ae8bc30bc2dc completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6784eacf4819095504e541d1d284d completed April 20, 2026, 7:02 p.m.
Created at: April 16, 2026, 11:24 a.m.