Triple

T20611436
Position Surface form Disambiguated ID Type / Status
Subject Bonnier family E506456 entity
Predicate associatedWith P37 FINISHED
Object Bonnier Books 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: Bonnier Books | Statement: [Bonnier family, associatedWith, Bonnier Books]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bonnier Books
Context triple: [Bonnier family, associatedWith, Bonnier Books]
  • A. Bonnier Books chosen
    Bonnier Books is a major European publishing company within the Bonnier Group, producing a wide range of books and digital content across multiple imprints and markets.
  • B. Albert Bonniers Förlag
    Albert Bonniers Förlag is one of Sweden’s oldest and most prominent publishing houses, known for its influential role in Scandinavian literature and its extensive catalog of fiction and non-fiction works.
  • C. Gyldendal
    Gyldendal is a major Scandinavian publishing house, best known as one of the oldest and most influential literary publishers in Norway and Denmark.
  • D. Andersen Press
    Andersen Press is a British independent publishing house best known for its award-winning children's and young adult books.
  • E. Little & Browne
    Little & Browne was an early 20th-century American architectural firm known for designing prominent Beaux-Arts and classical revival buildings.
  • 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_69e0b4bb2b4081908fa4a72444120f35 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6aad81bdc8190aa6f6164f406a468 completed April 20, 2026, 10:38 p.m.
Created at: April 16, 2026, 11:41 a.m.