Triple

T20949505
Position Surface form Disambiguated ID Type / Status
Subject Superman/Batman: Public Enemies E515941 entity
Predicate featureCharacter P23263 FINISHED
Object Katana 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: Katana | Statement: [Superman/Batman: Public Enemies, featureCharacter, Katana]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Katana
Context triple: [Superman/Batman: Public Enemies, featureCharacter, Katana]
  • A. Katana chosen
    Katana is a DC Comics superheroine and skilled Japanese swordswoman who wields a mystical soul-trapping blade and has been a member of teams such as the Outsiders and the Suicide Squad.
  • B. Katana
    Katana is a town and administrative division in Sri Lanka’s Western Province, situated within the Gampaha District.
  • C. Katano
    Katano is a city in Osaka Prefecture, Japan, known for its residential suburbs and proximity to the Osaka metropolitan area.
  • D. Tsurugi
    Tsurugi is a Japanese Shinkansen train service operating on the Hokuriku Shinkansen line, primarily providing all-stations shuttle connections between Toyama and Kanazawa.
  • E. Banryū
    Banryū was a Japanese warship that served in the late Edo period and took part in the Boshin War’s Naval Battle of Hakodate.
  • 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_69e0b4fcd678819087a304291f14330a completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6fadc08148190b4ff710f94462a26 completed April 21, 2026, 4:19 a.m.
Created at: April 16, 2026, 1:18 p.m.