Triple

T20384265
Position Surface form Disambiguated ID Type / Status
Subject Wicked (novel) E497919 entity
Predicate publisherImprint P2763 FINISHED
Object ReganBooks 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: ReganBooks | Statement: [Wicked (novel), publisherImprint, ReganBooks]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: ReganBooks
Context triple: [Wicked (novel), publisherImprint, ReganBooks]
  • A. ReganBooks chosen
    ReganBooks was a controversial imprint of HarperCollins known for publishing high-profile and politically charged non-fiction titles.
  • B. Red Books
    The "Red Books" are a series of illustrated landscape design proposals created by English landscape gardener Humphry Repton, renowned for their detailed before-and-after views and influential role in late 18th- and early 19th-century garden design.
  • C. Pan Books
    Pan Books is a British publishing imprint known for producing popular fiction and classic titles, including major science fiction works.
  • D. Target Books
    Target Books is a British publishing imprint best known for its novelizations of classic Doctor Who television stories.
  • E. The Book Fund
    The Book Fund was a charitable initiative established by Susannah Spurgeon to provide theological books and resources to impoverished pastors and ministers.
  • 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_69e0b4a5b7908190a972e4e7e698ae94 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e678b2ceec819091ad5205ee9b2174 completed April 20, 2026, 7:04 p.m.
Created at: April 16, 2026, 11:27 a.m.