Triple

T20290080
Position Surface form Disambiguated ID Type / Status
Subject Robert Evans E509994 entity
Predicate notableWork P4 FINISHED
Object Sliver 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: Sliver | Statement: [Robert Evans, notableWork, Sliver]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sliver
Context triple: [Robert Evans, notableWork, Sliver]
  • A. Sliver chosen
    Sliver is a 1993 erotic thriller film, based on an Ira Levin novel and starring Sharon Stone, about a woman who discovers disturbing surveillance and secrets in her New York apartment building.
  • B. Sliver
    "Sliver" is a raw, punk-influenced Nirvana song known for its catchy simplicity and depiction of childhood anxiety.
  • C. Sylver
    Sylver is a Belgian Eurodance and trance music group known for early-2000s club hits like "Turn the Tide" and "Forgiven."
  • D. Silfur
    Silfur is a contemplative modern classical album by composer and pianist Dustin O’Halloran, characterized by intimate piano pieces and atmospheric, minimalist arrangements.
  • E. Silvers
    Silvers is a surname most notably associated with Robert Silvers, the longtime editor and co-founder of The New York Review of Books.
  • 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_69e0b4c652388190b782cad965e5a098 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e67695d4d48190b932317d37aa95d9 completed April 20, 2026, 6:55 p.m.
Created at: April 16, 2026, 11:11 a.m.