Triple

T37511519
Position Surface form Disambiguated ID Type / Status
Subject Mei E932527 entity
Predicate formerRoleInGame P146886 FINISHED
Object defense hero LITERAL 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: defense hero | Statement: [Mei, formerRoleInGame, defense hero]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: formerRoleInGame
Context triple: [Mei, formerRoleInGame, defense hero]
  • A. formerCharacter
    Indicates that an entity was once a character in a work or series but is no longer an active or current character.
  • B. formerBandRole
    Indicates that an entity previously held a specific role or position in a band but no longer does.
  • C. formerRoleInOverwatch
    Indicates that an entity previously held a specific role or position within the Overwatch organization but no longer does.
  • D. formerPlayerType chosen
    Indicates that an entity previously had a specific player role or classification but no longer holds that status.
  • E. formerlyPlayedIn
    Indicates that an entity was previously a member of or participated in a particular team, group, or organization in the past but no longer does so.
  • F. None of above.

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_69f76ec730988190b5aa4f9cb9afd518 completed May 3, 2026, 3:50 p.m.
NER Named-entity recognition batch_6a00d508290081909f3d5dfbb2e80c8e completed May 10, 2026, 6:57 p.m.
PD Predicate disambiguation batch_6a00d49da4cc81909566ad286ec22292 completed May 10, 2026, 6:55 p.m.
Created at: May 3, 2026, 4:17 p.m.