Triple

T4709173
Position Surface form Disambiguated ID Type / Status
Subject Stalag 17 E104465 entity
Predicate castMember P1668 FINISHED
Object Robert Strauss E443559 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: Robert Strauss | Statement: [Stalag 17, castMember, Robert Strauss]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Robert Strauss
Context triple: [Stalag 17, castMember, Robert Strauss]
  • A. Robert Strauss chosen
    Robert Strauss was an American character actor best known for his comic and tough-guy roles in mid-20th-century films and stage productions.
  • B. Wilbur J. Cohen
    Wilbur J. Cohen was a prominent American social welfare expert and government official, often called the "father of Social Security" for his central role in shaping U.S. social insurance and welfare policy in the 20th century.
  • C. Henry Berman
    Henry Berman was an American film editor and producer known for his work on numerous classic Hollywood films.
  • D. Stanley Rosenblum
    Stanley Rosenblum was a film editor best known for his work on major Hollywood productions, including the boxing sequel "Rocky II."
  • E. Edward R. Pressman
    Edward R. Pressman was an influential American film producer known for backing distinctive and often risk-taking projects across independent and mainstream cinema, including films like "Wall Street," "Badlands," and "American Psycho."
  • 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_69bd43eac3c08190af7e4020c6c3704c completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd63ed2ed081908cd52570ba085806 completed March 20, 2026, 3:12 p.m.
NED1 Entity disambiguation (via context triple) batch_69beb0c5ef848190a19eb01622ade42a completed March 21, 2026, 2:52 p.m.
Created at: March 20, 2026, 1:17 p.m.