Triple

T7909708
Position Surface form Disambiguated ID Type / Status
Subject Agyness Deyn E183665 entity
Predicate discoveredAsModel P25799 FINISHED
Object in London while working in a fast-food restaurant 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: in London while working in a fast-food restaurant | Statement: [Agyness Deyn, discoveredAsModel, in London while working in a fast-food restaurant]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: discoveredAsModel
Context triple: [Agyness Deyn, discoveredAsModel, in London while working in a fast-food restaurant]
  • A. introducedAsModel
    Indicates that one entity is presented or identified to others in the role or capacity of a model.
  • B. discoveredAs chosen
    Indicates that one entity was first identified, found, or recognized in the role or form specified by another entity.
  • C. discoveredAsPartOf
    Indicates that something was found, identified, or revealed in the course of a larger activity, process, or investigation of which it formed a component.
  • D. isModelOf
    Indicates that one entity serves as a representation or abstraction that captures the structure or behavior of another entity.
  • E. discoveredResource
    Indicates that an entity has found, identified, or uncovered a particular resource.
  • 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_69ca828dec0c81908b8f55a4dbbb53ff completed March 30, 2026, 2:02 p.m.
NER Named-entity recognition batch_69cb3a5db9508190bbe92673ef5a7861 completed March 31, 2026, 3:07 a.m.
PD Predicate disambiguation batch_69cae92f9498819085277879e59aa072 completed March 30, 2026, 9:20 p.m.
Created at: March 30, 2026, 5:04 p.m.