Triple

T8182007
Position Surface form Disambiguated ID Type / Status
Subject Penguin Group E191083 entity
Predicate hasSubsidiary P254 FINISHED
Object Puffin Books E190728 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: Puffin Books | Statement: [Penguin Group, hasSubsidiary, Puffin Books]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Puffin Books
Context triple: [Penguin Group, hasSubsidiary, Puffin Books]
  • A. Puffin Books chosen
    Puffin Books is a prominent children’s book imprint known for publishing classic and contemporary literature for young readers worldwide.
  • B. 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.
  • C. Faber Children’s Books
    Faber Children’s Books is the children’s publishing imprint of the independent British publisher Faber and Faber, known for its high-quality and often award-winning books for young readers.
  • D. Ladybird Books
    Ladybird Books is a British children's publishing imprint best known for its small, affordable picture books and early reading titles.
  • E. Hayden Books
    Hayden Books was a technical and computer science publishing imprint known for producing influential programming and computing manuals in the late 20th century.
  • 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_69ca82c4538081909404325aa5639483 completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cb4c4db8748190aa785e0c70fac497 completed March 31, 2026, 4:23 a.m.
NED1 Entity disambiguation (via context triple) batch_69ce8861dc6481908ad83c99a2798f6e completed April 2, 2026, 3:16 p.m.
Created at: March 30, 2026, 5:40 p.m.