Triple

T20881960
Position Surface form Disambiguated ID Type / Status
Subject Telefon E514173 entity
Predicate screenwriter P2831 FINISHED
Object Stirling Silliphant 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: Stirling Silliphant | Statement: [Telefon, screenwriter, Stirling Silliphant]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Stirling Silliphant
Context triple: [Telefon, screenwriter, Stirling Silliphant]
  • A. Stirling Silliphant chosen
    Stirling Silliphant was an American screenwriter best known for his prolific work in film and television, including the Oscar-winning screenplay for "In the Heat of the Night."
  • B. Josh Mankiewicz
    Josh Mankiewicz is an American journalist best known as a longtime correspondent for NBC's newsmagazine program "Dateline NBC."
  • C. John Mankiewicz
    John Mankiewicz is an American television writer and producer known for his work on series such as House, House of Cards, and Bosch.
  • D. Tom Mankiewicz
    Tom Mankiewicz was an American screenwriter, director, and producer best known for his work on several James Bond films and the script for the 1978 film "Superman."
  • E. Stuart Schulberg
    Stuart Schulberg was an American filmmaker and producer best known for his work on World War II documentary films and postwar denazification projects, including the official film record of the Nuremberg Trials.
  • 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_69e0b4f733f081908a401c0b7beb0b9f completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c67a33548190b0f5ba58b001d387 completed April 21, 2026, 12:36 a.m.
Created at: April 16, 2026, 12:46 p.m.