Triple

T5230611
Position Surface form Disambiguated ID Type / Status
Subject Collins Atlas series E118100 entity
Predicate publisherSuccessor P2361 FINISHED
Object HarperCollins E65842 NE FINISHED

How this triple was built (3 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: HarperCollins | Statement: [Collins Atlas series, publisherSuccessor, HarperCollins]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: HarperCollins
Context triple: [Collins Atlas series, publisherSuccessor, HarperCollins]
  • A. HarperCollins chosen
    HarperCollins is a major global publishing company known for producing a wide range of fiction, non-fiction, and educational books.
  • B. Simon & Schuster
    Simon & Schuster is a major American publishing company known for producing a wide range of bestselling fiction and nonfiction books.
  • C. Penguin Random House
    Penguin Random House is a major global trade book publisher known for its extensive catalog of fiction and nonfiction titles across numerous imprints.
  • D. Macmillan Publishers
    Macmillan Publishers is a major global publishing company known for its wide range of academic, educational, and trade books and imprints.
  • E. Random House
    Random House is a major American book publishing company known for releasing a wide range of influential fiction and nonfiction titles.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: publisherSuccessor
Context triple: [Collins Atlas series, publisherSuccessor, HarperCollins]
  • A. formerPublisher chosen
    Indicates that one entity previously served as the publisher of another entity but no longer holds that role.
  • B. publisherOfWorkAppearingIn
    Indicates that an entity is the publisher responsible for issuing a work in which another specified work appears (e.g., as part of a collection, volume, or compilation).
  • C. subsequentPublication
    Indicates that one publication was released after another in time, making it a later or follow-up work relative to the first.
  • D. publishesAuthor
    Indicates that a publisher or publishing entity issues, releases, or makes publicly available works created by a specific author.
  • E. successorImprint
    Indicates that one imprint or edition directly follows and replaces another in a publication sequence.
  • F. None of above.

Provenance (4 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_69bd4466fb8c819083b806a79414d7e4 completed March 20, 2026, 12:58 p.m.
NER Named-entity recognition batch_69bd7b0093a88190aba381ba3f761408 completed March 20, 2026, 4:51 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf331e0e2881908b52da110384302a completed March 22, 2026, 12:09 a.m.
PD Predicate disambiguation batch_69bd77bf1ef08190bb3487b3f3ee088c completed March 20, 2026, 4:37 p.m.
Created at: March 20, 2026, 1:48 p.m.