Triple

T34138240
Position Surface form Disambiguated ID Type / Status
Subject Forbidden Fruit E875629 entity
Predicate vocalRoleOfKendrickLamar P181475 FINISHED
Object hook and ad-libs rather than full verse 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: hook and ad-libs rather than full verse | Statement: [Forbidden Fruit, vocalRoleOfKendrickLamar, hook and ad-libs rather than full verse]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: vocalRoleOfKendrickLamar
Context triple: [Forbidden Fruit, vocalRoleOfKendrickLamar, hook and ad-libs rather than full verse]
  • A. vocalRoleOfWale
    Indicates that an entity represents a vocal role or vocal contribution performed by the artist Wale in a work or recording.
  • B. vocalCounterpartType
    Indicates the type or category of a vocal counterpart relationship that one entity has to another (e.g., spoken, sung, dubbed, narrated).
  • C. vocalistIn
    Indicates that a person serves as a vocalist (singer) in a particular musical group, band, or ensemble.
  • D. hasNotableVocalType
    Indicates that an entity is associated with a specific, noteworthy type or quality of vocalization or voice.
  • E. hasMusicalVocalType
    Indicates that an entity is associated with a specific type or classification of singing voice.
  • F. None of above. chosen

Provenance (4 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_69f349aaeef08190a20e72a3fdeb7052 completed April 30, 2026, 12:23 p.m.
NER Named-entity recognition batch_69f7764ab1fc81909f9348db87bd7692 completed May 3, 2026, 4:22 p.m.
PD Predicate disambiguation batch_69f76905d9c88190b1ee810bc9ab644f completed May 3, 2026, 3:25 p.m.
PDg Predicate description generation batch_69f77648979c8190b6cdbb835ab8987c completed May 3, 2026, 4:22 p.m.
Created at: May 1, 2026, 1:53 a.m.