Triple

T22663817
Position Surface form Disambiguated ID Type / Status
Subject Ma (2019 film) E559729 entity
Predicate stars P1956 FINISHED
Object Diana Silvers 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: Diana Silvers | Statement: [Ma (2019 film), stars, Diana Silvers]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Diana Silvers
Context triple: [Ma (2019 film), stars, Diana Silvers]
  • A. Diana Silvers chosen
    Diana Silvers is an American actress and model best known for her roles in films like "Booksmart" and "Ma" and the Netflix series "Space Force."
  • B. Daisy Diamond
    Daisy Diamond is a 2007 Danish drama film directed by Simon Staho, known for Noomi Rapace’s intense and harrowing lead performance as a struggling young mother.
  • C. Sarah Silver
    Sarah Silver is known as the ex-wife of American dancer and chef Dean Sheremet.
  • D. Diana Rhodes
    Diana Rhodes is the mother of American filmmaker and "Euphoria" creator Sam Levinson.
  • E. Diana Finch
    Diana Finch is known as the daughter of the acclaimed English actor Peter Finch.
  • 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_69e2454a158c819093b8e35f5045efb6 completed April 17, 2026, 2:35 p.m.
NER Named-entity recognition batch_69f176617ed8819095a58a2c9f1e3918 completed April 29, 2026, 3:09 a.m.
Created at: April 17, 2026, 3:08 p.m.