Triple

T21652670
Position Surface form Disambiguated ID Type / Status
Subject Paul Varjak E534376 entity
Predicate relationshipTypeWith Holly Golightly P96108 FINISHED
Object friends-to-lovers 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: friends-to-lovers | Statement: [Paul Varjak, relationshipTypeWith Holly Golightly, friends-to-lovers]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: relationshipTypeWith Holly Golightly
Context triple: [Paul Varjak, relationshipTypeWith Holly Golightly, friends-to-lovers]
  • A. relationshipToHollyGolightly chosen
    Indicates the nature or type of relationship an entity has with Holly Golightly.
  • B. relationshipTypeWithSallyBowles
    Indicates the specific nature or category of relationship that an entity has with Sally Bowles.
  • C. relativeTypeToHappyGilmore
    Indicates that one entity is a specific type of relative or family relation to the entity Happy Gilmore.
  • D. relationshipTypeWith Alicia Johns
    Indicates the specific type or nature of the relationship that an entity has with Alicia Johns.
  • E. relationshipTypeWith J. C. Leyendecker
    Indicates the specific type or nature of the relationship that an entity has with J. C. Leyendecker.
  • 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_69e0c466aec88190ba39c7543dbc8ba2 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69ef591594a08190bf0ddd0a0c0922ba completed April 27, 2026, 12:39 p.m.
PD Predicate disambiguation batch_69e696826c3c81909270791e79760937 completed April 20, 2026, 9:11 p.m.
Created at: April 16, 2026, 6:36 p.m.