Triple

T19547211
Position Surface form Disambiguated ID Type / Status
Subject So Big E489104 entity
Predicate author P4 FINISHED
Object Edna Ferber 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: Edna Ferber | Statement: [So Big, author, Edna Ferber]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Edna Ferber
Context triple: [So Big, author, Edna Ferber]
  • A. Edna Ferber chosen
    Edna Ferber was a Pulitzer Prize–winning American novelist, short story writer, and playwright known for works like "Show Boat," "So Big," and "Giant," many of which were adapted for stage and film.
  • B. Fannie Hurst
    Fannie Hurst was a popular early 20th-century American novelist and short-story writer known for her melodramatic tales of women’s lives and social issues, many of which were adapted into successful films.
  • C. Sylvia Maibaum
    Sylvia Maibaum was the wife of American screenwriter Richard Maibaum, known for his work on many James Bond films.
  • D. Alix Kates Shulman
    Alix Kates Shulman is an American feminist writer and activist best known for her novel "Memoirs of an Ex-Prom Queen" and her contributions to second-wave feminism.
  • E. Van Druten
    Van Druten is the surname of John Van Druten, a notable 20th-century British-American playwright and director.
  • 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_69d8e8db5b6c8190984b61f91981f575 completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e63d2d8a6081908e9bb3a6f5d85896 completed April 20, 2026, 2:50 p.m.
Created at: April 10, 2026, 1:41 p.m.