Triple

T20611348
Position Surface form Disambiguated ID Type / Status
Subject Bonnier Group E506455 entity
Predicate foundedBy P104 FINISHED
Object Bonnier family 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 family | Statement: [Bonnier Group, foundedBy, Bonnier family]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bonnier family
Context triple: [Bonnier Group, foundedBy, Bonnier family]
  • A. Bonnier family chosen
    The Bonnier family is a prominent Swedish media dynasty that has owned and led the Bonnier media conglomerate for generations.
  • B. Wallenberg family
    The Wallenberg family is a prominent Swedish banking and industrial dynasty known for its major influence over Sweden’s economy and for notable members such as diplomat and Holocaust rescuer Raoul Wallenberg.
  • C. Bonnier Group
    Bonnier Group is a major Swedish family-owned media conglomerate with interests in publishing, broadcasting, and digital media across multiple countries.
  • D. Gannett family
    The Gannett family is an American media dynasty best known for founding and controlling the Gannett newspaper and publishing empire.
  • E. Reuter family
    The Reuter family is a prominent European dynasty best known for founding and controlling the Reuters news agency and for its influence in international finance and media.
  • 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.