Triple

T19754571
Position Surface form Disambiguated ID Type / Status
Subject Embassytown E474469 entity
Predicate originalPublisherImprint P2763 FINISHED
Object Macmillan UK 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: Macmillan UK | Statement: [Embassytown, originalPublisherImprint, Macmillan UK]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Macmillan UK
Context triple: [Embassytown, originalPublisherImprint, Macmillan UK]
  • A. Macmillan Publishers
    Macmillan Publishers is a major global publishing company known for its wide range of academic, educational, and trade books and imprints.
  • B. Pan Macmillan chosen
    Pan Macmillan is a major British publishing house known for producing a wide range of fiction and non-fiction titles by prominent authors.
  • C. Macmillan and Co.
    Macmillan and Co. was a prominent British publishing house known for issuing influential literary works by major authors of the 19th and early 20th centuries.
  • D. The Macmillan Company
    The Macmillan Company was a major American publishing house known for producing influential works in literature, education, and academic scholarship from the late 19th through the 20th century.
  • E. Macmillan Learning
    Macmillan Learning is an educational publishing and technology company that develops textbooks, digital learning tools, and course solutions for higher education and K–12 markets.
  • 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_69d8e51940a0819087bd2996f98da668 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e6529dada081909c5b4d65247c6032 completed April 20, 2026, 4:21 p.m.
Created at: April 10, 2026, 1:48 p.m.