Triple

T9698377
Position Surface form Disambiguated ID Type / Status
Subject Elaine de Kooning E234710 entity
Predicate wroteFor P1996 FINISHED
Object ARTnews E602208 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: ARTnews | Statement: [Elaine de Kooning, wroteFor, ARTnews]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: ARTnews
Context triple: [Elaine de Kooning, wroteFor, ARTnews]
  • A. Art News chosen
    Art News is a long-running American art magazine known for its coverage of contemporary and historical art, criticism, and art-world news.
  • B. Artsworld
    Artsworld was a UK-based television channel dedicated to arts and culture programming that later became known as Sky Arts.
  • C. ARTB
    ARTB is a U.S. Army training formation responsible for conducting advanced airborne and Ranger courses for soldiers.
  • D. Art Matters
    Art Matters is a book by British arts administrator and broadcaster Sir John Tusa that argues passionately for the value and public importance of the arts.
  • E. Ivorypress
    Ivorypress is a contemporary art and publishing platform based in Madrid, known for its artist’s books, exhibitions, and cultural projects at the intersection of art, architecture, and photography.
  • 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_69ca84cb580c8190a7e5f4b3bcdaf2a4 completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cd9d3d425c8190b652d84186b5ce9f completed April 1, 2026, 10:33 p.m.
NED1 Entity disambiguation (via context triple) batch_69d19125d3cc819082b3736d1b4ba802 completed April 4, 2026, 10:31 p.m.
Created at: March 30, 2026, 8:18 p.m.