Triple

T11008928
Position Surface form Disambiguated ID Type / Status
Subject Gilda E260196 entity
Predicate starring P1507 FINISHED
Object Steven Geray E336721 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: Steven Geray | Statement: [Gilda, starring, Steven Geray]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Steven Geray
Context triple: [Gilda, starring, Steven Geray]
  • A. Steven Geray chosen
    Steven Geray was a Hungarian-American character actor known for his numerous supporting roles in classic Hollywood films of the 1940s and 1950s.
  • B. Peter Garnsey
    Peter Garnsey is a prominent historian of the ancient world, particularly known for his influential scholarship on the social, economic, and legal history of the Roman Empire.
  • C. Philip Voss
    Philip Voss was a British actor known for his extensive work in theatre, television, and radio, including roles with the Royal Shakespeare Company and appearances in popular UK dramas.
  • D. Stephen Greenhorn
    Stephen Greenhorn is a Scottish playwright and screenwriter known for his work in theatre, television, and film, including creating the TV series "River City" and writing for "Doctor Who."
  • E. Stephen Volk
    Stephen Volk is a British screenwriter and author best known for his work in supernatural and horror drama for film and television.
  • 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_69d6aa9687448190b28d353b1b6a610e completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d7978810208190b8e2966ae67b6314 completed April 9, 2026, 12:11 p.m.
NED1 Entity disambiguation (via context triple) batch_69e37498b9fc8190860acede4f49ea4a completed April 18, 2026, 12:10 p.m.
Created at: April 8, 2026, 9:25 p.m.