Triple

T20104199
Position Surface form Disambiguated ID Type / Status
Subject T-Minus E180775 entity
Predicate hasWorkedWith P9615 FINISHED
Object Ludacris 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: Ludacris | Statement: [T-Minus, hasWorkedWith, Ludacris]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ludacris
Context triple: [T-Minus, hasWorkedWith, Ludacris]
  • A. Ludacris chosen
    Ludacris is an American rapper, actor, and entrepreneur known for his witty Southern hip hop style and roles in the Fast & Furious film franchise.
  • B. Sheek Louch
    Sheek Louch is an American rapper best known as a member of the hip hop group The LOX and co-founder of the D-Block record label.
  • C. Booba
    Booba is a prominent French rapper and entrepreneur known for his influential role in the French hip-hop scene and numerous hit albums and collaborations.
  • D. 50 Cent
    50 Cent is an American rapper, actor, and entrepreneur known for his influential early-2000s hip-hop albums and his breakout debut "Get Rich or Die Tryin'."
  • E. Nate Dogg
    Nate Dogg was an American singer and rapper renowned for his smooth, melodic hooks and pivotal contributions to West Coast G-funk and 1990s hip hop.
  • 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_69da62636cc08190982cc71733a17b8d completed April 11, 2026, 3:01 p.m.
NER Named-entity recognition batch_69e666daf73c819089f02ca6faa2c283 completed April 20, 2026, 5:48 p.m.
Created at: April 11, 2026, 11:27 p.m.