Triple

T19607492
Position Surface form Disambiguated ID Type / Status
Subject Desire E470645 entity
Predicate producer P490 FINISHED
Object Don DeVito 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: Don DeVito | Statement: [Desire, producer, Don DeVito]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Don DeVito
Context triple: [Desire, producer, Don DeVito]
  • A. Don DeVito chosen
    Don DeVito was an American record producer and music industry executive best known for his work with Bob Dylan at Columbia Records.
  • B. Hank DeVito
    Hank DeVito is an American country musician and renowned pedal steel guitarist best known for his work with Emmylou Harris and other prominent artists in the 1970s and 1980s.
  • C. Basil DeVito
    Basil DeVito is a sports executive best known for helping launch and lead the original XFL football league as its first commissioner.
  • D. Danny DeVito
    Danny DeVito is an American actor, comedian, and filmmaker known for his distinctive stature, gravelly voice, and memorable roles in film and television spanning several decades.
  • E. Harpo Soprano
    Harpo Soprano is the son of Janice Soprano in the television series "The Sopranos."
  • 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_69d8e510fa248190b7afb274a1d4cf73 completed April 10, 2026, 11:54 a.m.
NER Named-entity recognition batch_69e640c8aae8819086337e364724f1cb completed April 20, 2026, 3:05 p.m.
Created at: April 10, 2026, 1:43 p.m.