Triple

T19514150
Position Surface form Disambiguated ID Type / Status
Subject Painkiller E488233 entity
Predicate starring P1507 FINISHED
Object Uzo Aduba 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: Uzo Aduba | Statement: [Painkiller, starring, Uzo Aduba]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Uzo Aduba
Context triple: [Painkiller, starring, Uzo Aduba]
  • A. Uzo Aduba chosen
    Uzo Aduba is an Emmy Award–winning American actress best known for her acclaimed portrayal of Suzanne "Crazy Eyes" Warren on the Netflix series "Orange Is the New Black."
  • B. Yvonne Orji
    Yvonne Orji is a Nigerian-American actress and comedian best known for her role as Molly Carter on the HBO series "Insecure."
  • C. Jurnee Smollett-Bell
    Jurnee Smollett-Bell is an American actress known for her work in film and television, including prominent roles in projects like "Eve's Bayou," "Friday Night Lights," and "Lovecraft Country."
  • D. Adepero Oduye
    Adepero Oduye is an American actress and filmmaker best known for her acclaimed breakout performance in the independent drama film "Pariah."
  • E. Angela Bassett
    Angela Bassett is an acclaimed American actress known for her powerful performances in film and television, particularly in biographical and dramatic roles.
  • 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_69d8e8da8bec819081f400199491ccc3 completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e6359a7070819099d925447c80bf23 completed April 20, 2026, 2:18 p.m.
Created at: April 10, 2026, 1:40 p.m.