Triple

T8810766
Position Surface form Disambiguated ID Type / Status
Subject Attack! E209652 entity
Predicate stars P1956 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: [Attack!, stars, Robert Strauss]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Robert Strauss
Context triple: [Attack!, stars, 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. Everett Riskin
    Everett Riskin was an American film producer active during Hollywood’s studio era, known for his work on popular comedies and mystery films.
  • D. Richard A. Chaifetz
    Richard A. Chaifetz is an American neuropsychologist, entrepreneur, and philanthropist known for founding ComPsych Corporation and making major contributions to higher education and business schools.
  • E. Henry Berman
    Henry Berman was an American film editor and producer known for his work on numerous classic Hollywood films.
  • 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_69ca8363f3308190a47e3f1ebd51f613 completed March 30, 2026, 2:06 p.m.
NER Named-entity recognition batch_69cc5fed18f8819087b0282bf8c4208c completed March 31, 2026, 11:59 p.m.
NED1 Entity disambiguation (via context triple) batch_69d0772ba2808190b8b7948a09b8dee5 completed April 4, 2026, 2:27 a.m.
Created at: March 30, 2026, 6:45 p.m.