Triple

T9925253
Position Surface form Disambiguated ID Type / Status
Subject Jean-Michel Basquiat E187904 entity
Predicate collaboratedWith P435 FINISHED
Object Andy Warhol E5252 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: Andy Warhol | Statement: [Jean-Michel Basquiat, collaboratedWith, Andy Warhol]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Andy Warhol
Context triple: [Jean-Michel Basquiat, collaboratedWith, Andy Warhol]
  • A. Andy Warhol chosen
    Andy Warhol was a leading American Pop Art pioneer known for his iconic depictions of consumer goods and celebrities, such as his Campbell’s Soup Cans and Marilyn Monroe silkscreens.
  • B. John Warhola
    John Warhola was one of Andy Warhol’s older brothers, known for helping preserve and promote the artist’s legacy through the Andy Warhol Family Museum of Modern Art in Slovakia.
  • C. Paul Warhola
    Paul Warhola was an American artist and businessman best known as the older brother of pop art icon Andy Warhol.
  • D. Roy Lichtenstein
    Roy Lichtenstein was a leading American pop artist best known for his comic strip–inspired paintings that used bold colors, Ben-Day dots, and ironic commentary on mass culture.
  • E. Tom Wesselmann
    Tom Wesselmann was an American Pop artist best known for his bold, stylized depictions of the female nude and everyday consumer objects in vibrant, large-scale compositions.
  • 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_69ca82b22a688190b52c75bd48429c10 completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cdb598651081908286763ff56ba57c completed April 2, 2026, 12:17 a.m.
NED1 Entity disambiguation (via context triple) batch_69d20e143660819097a9fa96365bc25a completed April 5, 2026, 7:24 a.m.
Created at: March 30, 2026, 8:43 p.m.