Triple

T7342522
Position Surface form Disambiguated ID Type / Status
Subject Faithfully E169290 entity
Predicate producer P490 FINISHED
Object Vidal Davis E386799 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: Vidal Davis | Statement: [Faithfully, producer, Vidal Davis]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Vidal Davis
Context triple: [Faithfully, producer, Vidal Davis]
  • A. Vidal Davis chosen
    Vidal Davis is an American drummer and record producer best known as one half of the R&B and hip-hop production duo Dre & Vidal.
  • B. Rennie Davis
    Rennie Davis was a prominent American anti–Vietnam War activist and one of the Chicago Seven defendants tried for protesting at the 1968 Democratic National Convention.
  • C. Altovise Davis
    Altovise Davis was an American dancer and actress best known as the longtime wife and widow of entertainer Sammy Davis Jr.
  • D. Kay Hilliard
    Kay Hilliard is the central female protagonist in the 1956 musical film "The Opposite Sex," navigating love, betrayal, and personal growth within the world of high society marriages.
  • E. Rolando Blackman
    Rolando Blackman is a former NBA All-Star shooting guard best known for his standout collegiate career at Kansas State and his long tenure with the Dallas Mavericks in the 1980s and early 1990s.
  • 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_69c68a57710481909f0c1f3c6ebdb6f2 completed March 27, 2026, 1:47 p.m.
NER Named-entity recognition batch_69c6f0db2db8819088c4bed5d65571f6 completed March 27, 2026, 9:04 p.m.
NED1 Entity disambiguation (via context triple) batch_69c810cbd78c8190934dd5d4baa1a0a7 completed March 28, 2026, 5:33 p.m.
Created at: March 27, 2026, 3:04 p.m.