Triple

T19470513
Position Surface form Disambiguated ID Type / Status
Subject Blonde Roots E487109 entity
Predicate publisher P29 FINISHED
Object Riverhead Books 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: Riverhead Books | Statement: [Blonde Roots, publisher, Riverhead Books]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Riverhead Books
Context triple: [Blonde Roots, publisher, Riverhead Books]
  • A. Riverhead Books chosen
    Riverhead Books is a prominent American publishing imprint known for its innovative and literary fiction and nonfiction titles by acclaimed contemporary authors.
  • B. Mulholland Books
    Mulholland Books is a crime, mystery, and suspense-focused publishing imprint of Little, Brown and Company known for thriller and noir fiction.
  • C. St. Martin's Press
    St. Martin's Press is a major American book publisher known for its wide range of commercial fiction and nonfiction titles.
  • D. Grove Press
    Grove Press is an influential American publishing house known for championing avant-garde, politically radical, and previously censored literature.
  • E. Flatiron Books
    Flatiron Books is an American publishing imprint of Macmillan known for releasing high-profile nonfiction and literary fiction titles.
  • 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_69d8e8d86d608190bd199a98d0297f27 completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e633e809008190b0021d41b99f9700 completed April 20, 2026, 2:10 p.m.
Created at: April 10, 2026, 1:39 p.m.