Triple

T29790339
Position Surface form Disambiguated ID Type / Status
Subject Pull Up to the Bumper E756384 entity
Predicate associatedPerformerImage P27923 FINISHED
Object Grace Jones’s avant-garde persona 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: Grace Jones’s avant-garde persona | Statement: [Pull Up to the Bumper, associatedPerformerImage, Grace Jones’s avant-garde persona]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: associatedPerformerImage
Context triple: [Pull Up to the Bumper, associatedPerformerImage, Grace Jones’s avant-garde persona]
  • A. isAssociatedWithArtistImage chosen
    Indicates a relationship where an entity is linked or connected to an image that represents or depicts an artist.
  • B. associatedWithActorImage
    Indicates a relationship where something (such as data, content, or a record) is linked or connected to an actor’s image.
  • C. associatedWithPerformer
    Indicates a relationship in which something (such as a work, event, or role) is connected or linked to a specific performer.
  • D. associatedPerformerPersona
    Indicates a relationship where a performer is linked to a specific persona or role identity they adopt in their performances.
  • E. associatedWithMediaImage
    Indicates a relationship where an entity is linked or connected to a specific media image, such as a photo, illustration, or graphic file.
  • 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_69f22451fb748190bbdbab401280affb completed April 29, 2026, 3:31 p.m.
NER Named-entity recognition batch_6a037c876524819098545e6037d3107d completed May 12, 2026, 7:16 p.m.
PD Predicate disambiguation batch_6a0379e0f3d88190a4ee7b0673f1ef90 completed May 12, 2026, 7:05 p.m.
Created at: April 29, 2026, 5:12 p.m.