Triple

T10072808
Position Surface form Disambiguated ID Type / Status
Subject Nadia Salerno-Sonnenberg E213670 entity
Predicate studiedUnder P7251 FINISHED
Object Dorothy DeLay E184651 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: Dorothy DeLay | Statement: [Nadia Salerno-Sonnenberg, studiedUnder, Dorothy DeLay]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dorothy DeLay
Context triple: [Nadia Salerno-Sonnenberg, studiedUnder, Dorothy DeLay]
  • A. Dorothy DeLay chosen
    Dorothy DeLay was a renowned American violin teacher at the Juilliard School, celebrated for mentoring many of the 20th century’s leading virtuoso violinists.
  • B. Dorothy Shaw
    Dorothy Shaw is the witty, down-to-earth brunette showgirl and best friend of Lorelei Lee in the musical comedy "Gentlemen Prefer Blondes."
  • C. Dorothy Bridges
    Dorothy Bridges was an American actress and poet best known as the matriarch of the Bridges acting family and the wife of actor Lloyd Bridges.
  • D. Marilyn Vance
    Marilyn Vance is an American costume designer known for her influential work on numerous popular films, including iconic 1980s and 1990s movies.
  • E. Sol Lesser
    Sol Lesser was an American film producer best known for his extensive work on the Tarzan movie series during 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_69ca839add308190b57d53b4ec21f2d0 completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cdd013c9d0819091ebe6fc399832de completed April 2, 2026, 2:10 a.m.
NED1 Entity disambiguation (via context triple) batch_69d29ab376488190bfb3efdb3f240cca completed April 5, 2026, 5:24 p.m.
Created at: March 30, 2026, 8:59 p.m.