Triple

T19993915
Position Surface form Disambiguated ID Type / Status
Subject Dave Kelly E494133 entity
Predicate collaboratedWith P435 FINISHED
Object Mavado NE NERFINISHED

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: Mavado | Statement: [Dave Kelly, collaboratedWith, Mavado]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mavado
Context triple: [Dave Kelly, collaboratedWith, Mavado]
  • A. Mavado chosen
    Mavado is a Jamaican dancehall and reggae artist known for his gritty vocal style and influential role in modern dancehall music.
  • B. Sizzla
    Sizzla is a prominent Jamaican reggae and dancehall artist known for his prolific output and influential role in the modern roots reggae and Rastafarian music movement.
  • C. Naira Marley
    Naira Marley is a Nigerian singer and rapper known for his street-hop anthems, controversial lyrics, and leading the fanbase known as the "Marlian" movement.
  • D. Ladipoe
    Ladipoe is a Nigerian rapper and songwriter known for his clever wordplay and contributions to the contemporary Afrobeats and hip-hop scene.
  • E. Joe de Graft
    Joe de Graft was a Ghanaian playwright, actor, and director known for his influential contributions to African theatre and film.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69da626b2d748190886981ea90c8b2ea completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e65fe2036c8190b9f313215ad44e87 completed April 20, 2026, 5:18 p.m.
Created at: April 11, 2026, 3:31 p.m.