Triple

T20191854
Position Surface form Disambiguated ID Type / Status
Subject Star Warrior E492995 entity
Predicate notableMember P10 FINISHED
Object Meta Knight 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: Meta Knight | Statement: [Star Warrior, notableMember, Meta Knight]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Meta Knight
Context triple: [Star Warrior, notableMember, Meta Knight]
  • A. Meta Knight chosen
    Meta Knight is a mysterious, masked swordsman from the Kirby video game series, known for his chivalrous demeanor, powerful combat skills, and ambiguous role as both rival and ally to Kirby.
  • B. Jack Knight
    Jack Knight is a music artist known for his guest vocal contributions and collaborations in contemporary recordings.
  • C. Jack Knight
    Jack Knight is a DC Comics superhero who serves as a modern incarnation of Starman, known for his reluctant heroism and use of a cosmic-powered staff.
  • D. Kristoff Krane
    Kristoff Krane is an American underground hip hop artist known for his introspective lyrics, experimental style, and collaborations within the Minneapolis music scene.
  • E. Gene Lockhart
    Gene Lockhart was a Canadian-American character actor known for his prolific work in Hollywood films and on stage during the 1930s and 1940s.
  • 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_69da6268a034819081cbd9ea5a1c9475 completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e66ad593f88190a1e534fed38b3cd7 completed April 20, 2026, 6:05 p.m.
Created at: April 11, 2026, 11:37 p.m.