Triple

T7289550
Position Surface form Disambiguated ID Type / Status
Subject Side to Side E163956 entity
Predicate performer P1363 FINISHED
Object Nicki Minaj E64115 NE 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: Nicki Minaj | Statement: [Side to Side, performer, Nicki Minaj]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Nicki Minaj
Context triple: [Side to Side, performer, Nicki Minaj]
  • A. Nicki Minaj chosen
    Nicki Minaj is a Trinidadian-born American rapper, singer, and songwriter known for her animated flow, alter egos, and major influence on contemporary hip hop and pop music.
  • B. Cardi B
    Cardi B is an American rapper, songwriter, and media personality known for her chart-topping hits, outspoken persona, and significant impact on contemporary hip hop.
  • C. Nicki
    Nicki is a professional basketball coach best known for her work in women's basketball, including in the WNBA and NCAA.
  • D. Remy Ma
    Remy Ma is an American rapper from the Bronx known for her sharp lyricism, prominent role in early-2000s hip-hop, and membership in Fat Joe’s Terror Squad.
  • E. Blac Chyna
    Blac Chyna is an American model, entrepreneur, and media personality known for her appearances in hip-hop music videos, reality television, and her high-profile relationships in the entertainment industry.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

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_69c6886093b88190a254b1ce6db8bae7 completed March 27, 2026, 1:38 p.m.
NER Named-entity recognition batch_69c6eb6bde448190b52852c916a8059d completed March 27, 2026, 8:41 p.m.
NED1 Entity disambiguation (via context triple) batch_69c7e53ab41c8190b081e90fa6a1145c completed March 28, 2026, 2:27 p.m.
Created at: March 27, 2026, 3 p.m.