Triple

T37550983
Position Surface form Disambiguated ID Type / Status
Subject Death Knight E933588 entity
Predicate playstyleTheme P3775 FINISHED
Object dark knight 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: dark knight | Statement: [Death Knight, playstyleTheme, dark knight]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: playstyleTheme
Context triple: [Death Knight, playstyleTheme, dark knight]
  • A. playstyleBenefit
    Indicates that one playstyle provides an advantage, improvement, or positive effect to a player or entity.
  • B. styleOfPlay chosen
    Indicates the characteristic manner or approach in which an entity performs or behaves, especially in a game, sport, or artistic context.
  • C. playsInStyleOf
    Indicates that one entity performs, creates, or behaves in a manner characteristic of another entity’s style.
  • D. PoseThemes
    Indicates that a particular pose expresses, embodies, or is associated with certain thematic ideas or concepts.
  • E. abilityTheme
    Indicates that an entity possesses, embodies, or is characterized by a particular ability or capability.
  • 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_69f76eca55bc8190acf25741793d5dac completed May 3, 2026, 3:50 p.m.
NER Named-entity recognition batch_69fccdd496048190bca801a8a9eecb62 completed May 7, 2026, 5:37 p.m.
PD Predicate disambiguation batch_69fcccee6240819084680887731ff64b completed May 7, 2026, 5:33 p.m.
Created at: May 3, 2026, 4:17 p.m.