Triple

T21906202
Position Surface form Disambiguated ID Type / Status
Subject Ilya Salkind E540944 entity
Predicate collaboratedWith P435 FINISHED
Object Richard Donner 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: Richard Donner | Statement: [Ilya Salkind, collaboratedWith, Richard Donner]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Richard Donner
Context triple: [Ilya Salkind, collaboratedWith, Richard Donner]
  • A. Richard Donner chosen
    Richard Donner was an influential American film director and producer best known for blockbuster hits such as "Superman," "The Omen," and the "Lethal Weapon" series.
  • B. Robert Donner
    Robert Donner was an American character actor best known for his eccentric comedic roles in film and television from the 1960s through the 1980s.
  • C. Jonathan Mostow
    Jonathan Mostow is an American film director best known for helming the science fiction action sequel "Terminator 3: Rise of the Machines."
  • D. Jerry Schatzberg
    Jerry Schatzberg is an American photographer and film director known for his influential work in 1960s music photography and for directing acclaimed films such as "Panic in Needle Park" and "Scarecrow."
  • E. Richard Fleischer
    Richard Fleischer was an American film director known for a diverse body of work that included noir, science fiction, historical epics, and big-budget Hollywood adventures.
  • 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_69e0c47b4e8c81908c8076eaa4c8e4f2 completed April 16, 2026, 11:14 a.m.
NER Named-entity recognition batch_69f121d62a648190af7074251dc6a03a completed April 28, 2026, 9:08 p.m.
Created at: April 16, 2026, 7:37 p.m.