Triple

T13749650
Position Surface form Disambiguated ID Type / Status
Subject Digital Bullet E330307 entity
Predicate artist P184 FINISHED
Object Dead Prez E421383 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: Dead Prez | Statement: [Digital Bullet, artist, Dead Prez]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dead Prez
Context triple: [Digital Bullet, artist, Dead Prez]
  • A. Dead Prez chosen
    Dead Prez is an American hip hop duo known for their politically charged, socially conscious lyrics and militant, revolutionary themes.
  • B. Ghostface Killah
    Ghostface Killah is an American rapper best known as a prominent member of the Wu-Tang Clan and for his vivid, storytelling solo work.
  • C. Pharoahe Monch
    Pharoahe Monch is an American rapper and lyricist known for his complex wordplay, intricate rhyme schemes, and influential work in underground hip-hop.
  • D. Elzhi
    Elzhi is an American rapper and lyricist from Detroit known for his intricate wordplay and work as a former member of the influential hip-hop group Slum Village.
  • E. Rahzel
    Rahzel is an American beatboxer and vocal percussionist renowned for his innovative ability to simultaneously sing and beatbox, and for his prominent work with the hip hop group The Roots.
  • 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_69d81c573f288190aa2403d484fa3d49 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de02148c208190a882927905a861a6 completed April 14, 2026, 9 a.m.
NED1 Entity disambiguation (via context triple) batch_69f7a854098c8190983d142c9930962b completed May 3, 2026, 7:56 p.m.
Created at: April 9, 2026, 10:08 p.m.