Triple

T13541370
Position Surface form Disambiguated ID Type / Status
Subject Dani Dennison E323392 entity
Predicate costumeOnHalloween P69136 FINISHED
Object witch costume 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: witch costume | Statement: [Dani Dennison, costumeOnHalloween, witch costume]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: costumeOnHalloween
Context triple: [Dani Dennison, costumeOnHalloween, witch costume]
  • A. costume
    Indicates that one entity is wearing, dressed in, or outfitted with the other entity as a costume.
  • B. costumeType
    Indicates the specific kind or category of costume associated with an entity.
  • C. costumeContext chosen
    Indicates the situational or narrative context in which a costume is used, such as the event, setting, or role it is associated with.
  • D. costumeInspiration
    Indicates that one entity serves as the creative source or model for another entity’s costume design.
  • E. costumeElement
    Indicates that one item functions as a component or part of another item's costume.
  • 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_69d8076776248190bdf0d4fa1f85a5fc completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69dbafd8ba10819098faadcc6adf251e completed April 12, 2026, 2:44 p.m.
PD Predicate disambiguation batch_69dbae1046c48190b4ee98c6c9cb9d85 completed April 12, 2026, 2:37 p.m.
Created at: April 9, 2026, 9:45 p.m.