Triple

T22188551
Position Surface form Disambiguated ID Type / Status
Subject Arrow of God E548357 entity
Predicate publisher P29 FINISHED
Object Heinemann 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: Heinemann | Statement: [Arrow of God, publisher, Heinemann]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Heinemann
Context triple: [Arrow of God, publisher, Heinemann]
  • A. Heinemann publishing group chosen
    Heinemann publishing group is a British publishing company known for its literary fiction, educational materials, and classic literature imprints.
  • B. Hodder & Stoughton
    Hodder & Stoughton is a major British publishing house known for producing a wide range of fiction, non-fiction, and religious titles.
  • C. Jonathan Cape
    Jonathan Cape is a renowned British publishing house best known for issuing Ian Fleming’s James Bond novels and other major 20th-century literary works.
  • D. Penguin Books
    Penguin Books is a major British publishing house known for its influential paperback editions and wide range of literary and non-fiction titles.
  • E. Bodley Head
    Bodley Head is a British publishing house known for its literary fiction, non-fiction, and classic works.
  • 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_69e11e3e0c7c8190b30d278845e2497e completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f12aab3d2c81908a3b5a5c127c4aac completed April 28, 2026, 9:46 p.m.
Created at: April 16, 2026, 8:35 p.m.