Triple

T10091101
Position Surface form Disambiguated ID Type / Status
Subject Soylent Green E215345 entity
Predicate producer P490 FINISHED
Object Walter Seltzer E796979 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: Walter Seltzer | Statement: [Soylent Green, producer, Walter Seltzer]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Walter Seltzer
Context triple: [Soylent Green, producer, Walter Seltzer]
  • A. Walter Seltzer chosen
    Walter Seltzer was an American film producer known for his work on science fiction and genre films in the mid-20th century.
  • B. John Altschuler
    John Altschuler is an American television writer and producer best known for co-creating and producing the animated series "King of the Hill" and "Silicon Valley."
  • C. Steven Fierberg
    Steven Fierberg is an American cinematographer known for his work on feature films and television series, including the romantic drama "Love & Other Drugs."
  • D. Jerry Bresler
    Jerry Bresler was an American film producer active in mid-20th-century Hollywood, known for working on large-scale studio productions.
  • E. Seymour Boorstein
    Seymour Boorstein was an American psychiatrist and psychoanalyst known for integrating psychoanalytic theory with spirituality and transpersonal psychology.
  • 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_69ca83a1eed081908b2e9580f2ebeea7 completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cdd05aa02081908fba02e7085c6d7c completed April 2, 2026, 2:11 a.m.
NED1 Entity disambiguation (via context triple) batch_69de54a30b748190bb791078e9dde442 completed April 14, 2026, 2:52 p.m.
Created at: March 30, 2026, 9:01 p.m.