Triple

T1308070
Position Surface form Disambiguated ID Type / Status
Subject Hachette Book Group E27925 entity
Predicate subsidiary P258 FINISHED
Object Back Bay Books E77991 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: Back Bay Books | Statement: [Hachette Book Group, subsidiary, Back Bay Books]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Back Bay Books
Context triple: [Hachette Book Group, subsidiary, Back Bay Books]
  • A. Back Bay Books chosen
    Back Bay Books is a paperback imprint of the publishing house Little, Brown and Company, known for reissuing literary fiction and nonfiction titles.
  • B. New York Review Books
    New York Review Books is an independent publishing imprint known for its curated series of classic, overlooked, and international works of literature and nonfiction.
  • C. Grove Press
    Grove Press is an influential American publishing house known for championing avant-garde, politically radical, and previously censored literature.
  • D. Mulholland Books
    Mulholland Books is a crime, mystery, and suspense-focused publishing imprint of Little, Brown and Company known for thriller and noir fiction.
  • E. Mariner Books
    Mariner Books is a publishing imprint known for producing a wide range of literary fiction, nonfiction, and classic reprints.
  • 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_69a496d7d83481908f83085854e51328 completed March 1, 2026, 7:43 p.m.
NER Named-entity recognition batch_69a4c13806b48190a0db33f8e5d53734 completed March 1, 2026, 10:44 p.m.
NED1 Entity disambiguation (via context triple) batch_69acb308fdcc8190b33da42f16cd65dd completed March 7, 2026, 11:21 p.m.
Created at: March 1, 2026, 7:51 p.m.