Triple

T20898440
Position Surface form Disambiguated ID Type / Status
Subject Mississippi Grind E514604 entity
Predicate starring P1507 FINISHED
Object Alfre Woodard 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: Alfre Woodard | Statement: [Mississippi Grind, starring, Alfre Woodard]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Alfre Woodard
Context triple: [Mississippi Grind, starring, Alfre Woodard]
  • A. Alfre Woodard chosen
    Alfre Woodard is an acclaimed American actress known for her powerful performances in film, television, and theater, often portraying complex, socially resonant characters.
  • B. Angela Bettis
    Angela Bettis is an American actress and filmmaker best known for her roles in psychological horror films such as "May" and the 2002 television adaptation of "Carrie."
  • C. Stockard Channing
    Stockard Channing is an American actress best known for her roles as Rizzo in the film "Grease" and First Lady Abbey Bartlet on the television series "The West Wing."
  • D. Shirley Washington
    Shirley Washington is an American actress best known for her film and television work in the 1970s and 1980s.
  • E. Mary McDonnell
    Mary McDonnell is an American actress known for her acclaimed film and television roles, including her work in dramas and science fiction such as "Dances with Wolves" and "Battlestar Galactica."
  • 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_69e0b4f7ebe48190952a85547a0f31a1 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6e8f826788190b11008cc94b2a4e4 completed April 21, 2026, 3:03 a.m.
Created at: April 16, 2026, 12:47 p.m.