Triple

T20668119
Position Surface form Disambiguated ID Type / Status
Subject Kathryn Grayson E507945 entity
Predicate givenName P17 FINISHED
Object Zelma 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: Zelma | Statement: [Kathryn Grayson, givenName, Zelma]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Zelma
Context triple: [Kathryn Grayson, givenName, Zelma]
  • A. Zelma chosen
    Zelma is a feminine given name of Hebrew origin, often considered a variant of Selma or Anselma.
  • B. Clarita
    Clarita is a Spanish diminutive form of the given name Clara, often used as an affectionate or familiar variant.
  • C. Melva
    Melva is a character in Richard Bruce Nugent’s modernist short story "Smoke, Lilies and Jade," which explores themes of race, sexuality, and artistic identity during the Harlem Renaissance.
  • D. Zelma Atwood
    Zelma Atwood is best known as the widow of legendary soul singer Otis Redding and the longtime steward of his musical legacy and estate.
  • E. Antonia Van Drimmelen
    Antonia Van Drimmelen is a film editor known for her work on the political drama film "Charlie Wilson's War."
  • 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_69e0b4c059bc81908ea762cd73ea4424 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6b5c4c4608190ae17da4a59e5ae80 completed April 20, 2026, 11:24 p.m.
Created at: April 16, 2026, 11:44 a.m.