Triple

T1323287
Position Surface form Disambiguated ID Type / Status
Subject Blowback E28267 entity
Predicate publisher P29 FINISHED
Object Metropolitan Books E8357 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: Metropolitan Books | Statement: [Blowback, publisher, Metropolitan Books]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Metropolitan Books
Context triple: [Blowback, publisher, Metropolitan Books]
  • A. Metropolitan Books chosen
    Metropolitan Books is an American publishing imprint known for releasing influential and often politically engaged nonfiction works by prominent intellectuals and public thinkers.
  • B. Pantheon Books
    Pantheon Books is an American publishing imprint known for releasing influential works in politics, history, and critical theory.
  • C. Perseus Books Group
    Perseus Books Group is an American publishing company known for its diverse portfolio of imprints and distribution services for independent publishers.
  • D. Carroll & Graf
    Carroll & Graf was an American publishing imprint known for its eclectic catalog of literary fiction, crime novels, and nonfiction titles.
  • E. Anchor Books
    Anchor Books is a paperback publishing imprint known for issuing classic and contemporary literary works, often in affordable and widely distributed editions.
  • 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_69a498540a2481909e807a762280d3ba completed March 1, 2026, 7:49 p.m.
NER Named-entity recognition batch_69a4c19caa148190a1f5be734b7d9005 completed March 1, 2026, 10:45 p.m.
NED1 Entity disambiguation (via context triple) batch_69acd47471108190b01121b384d871aa completed March 8, 2026, 1:44 a.m.
Created at: March 1, 2026, 7:55 p.m.