Triple

T1451648
Position Surface form Disambiguated ID Type / Status
Subject Walkaway E31303 entity
Predicate publisher P29 FINISHED
Object Tor Books E159906 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: Tor Books | Statement: [Walkaway, publisher, Tor Books]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tor Books
Context triple: [Walkaway, publisher, Tor Books]
  • A. Tor Books chosen
    Tor Books is a major American science fiction and fantasy publishing imprint known for releasing influential genre novels and series.
  • B. Pocket Books
    Pocket Books is a long-running American mass-market paperback publisher known for popular fiction and non-fiction titles, operating as an imprint of Simon & Schuster.
  • C. Hyperion Books
    Hyperion Books is an American publishing imprint, originally founded by The Walt Disney Company, known for releasing a wide range of popular fiction and non-fiction titles.
  • D. Del Rey Books
    Del Rey Books is a prominent American publishing imprint best known for its science fiction and fantasy titles.
  • E. Prometheus Books
    Prometheus Books is an American publishing company known for its focus on humanism, skepticism, and science-oriented non-fiction.
  • 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_69a499171a28819085b993a3ac78e363 completed March 1, 2026, 7:52 p.m.
NER Named-entity recognition batch_69a4c57bc0908190a57e6bc3d20d5e3c completed March 1, 2026, 11:02 p.m.
NED1 Entity disambiguation (via context triple) batch_69ad08c6f7c881908d1ef9f7897895a6 completed March 8, 2026, 5:27 a.m.
Created at: March 1, 2026, 8 p.m.