Triple

T8527083
Position Surface form Disambiguated ID Type / Status
Subject Sylvia Sidney E201843 entity
Predicate spouse P13 FINISHED
Object Luther Adler E383219 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: Luther Adler | Statement: [Sylvia Sidney, spouse, Luther Adler]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Luther Adler
Context triple: [Sylvia Sidney, spouse, Luther Adler]
  • A. Luther Adler chosen
    Luther Adler was an American stage and film actor and director associated with the development of method acting and influential mid-20th-century theater in the United States.
  • B. Arthur Simon Flegenheimer
    Arthur Simon Flegenheimer, better known as Dutch Schultz, was a notorious New York City mobster and bootlegger during the Prohibition era.
  • C. Herman Cohen
    Herman Cohen was an American film producer best known for his low-budget horror and exploitation films of the 1950s and 1960s.
  • D. Leo Löwenthal
    Leo Löwenthal was a German sociologist and literary critic associated with the Frankfurt School, known for his analyses of mass culture, literature, and the sociology of intellectuals.
  • E. Leo Friedlander
    Leo Friedlander was an American sculptor known for his large-scale public monuments and architectural sculpture, particularly in the mid-20th century.
  • 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_69ca83228b24819085d22e7dc99f5d94 completed March 30, 2026, 2:05 p.m.
NER Named-entity recognition batch_69cbe6477100819081fa20cb6b8ea3d7 completed March 31, 2026, 3:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69cf42459a048190a5c480f4a212607a completed April 3, 2026, 4:29 a.m.
Created at: March 30, 2026, 6:16 p.m.