Triple

T23220539
Position Surface form Disambiguated ID Type / Status
Subject Herbst Theatre E580877 entity
Predicate namedAfter P63 FINISHED
Object Edyth Susie Herbst 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: Edyth Susie Herbst | Statement: [Herbst Theatre, namedAfter, Edyth Susie Herbst]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Edyth Susie Herbst
Context triple: [Herbst Theatre, namedAfter, Edyth Susie Herbst]
  • A. Edyth Susie Herbst chosen
    Edyth Susie Herbst was a benefactor and namesake whose legacy is commemorated by the historic Herbst Theatre in San Francisco.
  • B. Edythe Eyssell
    Edythe Eyssell was the wife of prominent Kansas City real estate developer J. C. Nichols and a member of a notable local social and civic family.
  • C. Susie Dietter
    Susie Dietter is an American animation director best known for her work on the television series "The Simpsons."
  • D. Edythe Marrenner
    Edythe Marrenner was the birth name of Susan Hayward, the American film actress who became a major Hollywood star and Academy Award winner in the mid-20th century.
  • E. Elizabeth Paepcke
    Elizabeth Paepcke was an American philanthropist and cultural visionary who, with her husband Walter, played a central role in transforming Aspen, Colorado into an international center for arts, ideas, and intellectual dialogue.
  • 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_69e2460389408190be74f41d217799a9 completed April 17, 2026, 2:38 p.m.
NER Named-entity recognition batch_69f1916870148190853874e6cf26bbc7 completed April 29, 2026, 5:04 a.m.
Created at: April 17, 2026, 4:08 p.m.