Triple

T20491011
Position Surface form Disambiguated ID Type / Status
Subject David Dornsife E502743 entity
Predicate spouse P13 FINISHED
Object Dana Dornsife 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: Dana Dornsife | Statement: [David Dornsife, spouse, Dana Dornsife]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dana Dornsife
Context triple: [David Dornsife, spouse, Dana Dornsife]
  • A. Dana Dornsife chosen
    Dana Dornsife is an American philanthropist and business leader known for her major contributions to health, education, and cancer research initiatives.
  • B. Dana A. Dorsey
    Dana A. Dorsey was a prominent African American businessman and Miami’s first Black millionaire, known for his significant contributions to real estate and community development in the early 20th century.
  • C. Jennifer Bransford
    Jennifer Bransford is an American actress best known for her work in television soap operas and other TV roles.
  • D. Kimberly Loya
    Kimberly Loya is a former member of the experimental indie rock band Dirty Projectors.
  • E. Dana Stewart
    Dana Stewart is the daughter of Australian screenwriter and director Jules Mann-Stewart and a member of the Stewart family connected to the film industry.
  • 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_69e0b4b0373881909dd3e9387f82eab4 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e69cb8e7848190a1dc497a10ae798c completed April 20, 2026, 9:38 p.m.
Created at: April 16, 2026, 11:35 a.m.