Triple

T14378417
Position Surface form Disambiguated ID Type / Status
Subject HS.fi E356534 entity
Predicate parentOrganization P254 FINISHED
Object Sanoma E356531 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: Sanoma | Statement: [HS.fi, parentOrganization, Sanoma]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sanoma
Context triple: [HS.fi, parentOrganization, Sanoma]
  • A. Sanoma chosen
    Sanoma is a major Finnish media and learning company known for its newspapers, magazines, digital media, and educational publishing across Europe.
  • B. Bonnier Group
    Bonnier Group is a major Swedish family-owned media conglomerate with interests in publishing, broadcasting, and digital media across multiple countries.
  • C. Egmont Group
    Egmont Group is an international network of national financial intelligence units that collaborate to combat money laundering, terrorist financing, and other financial crimes.
  • D. Egmont Group
    Egmont Group is a Danish media conglomerate and charitable foundation that operates in publishing, film, television, and digital entertainment across multiple countries.
  • E. Ringier
    Ringier is a Swiss-based international media company that owns and operates a wide portfolio of newspapers, magazines, digital platforms, and entertainment brands across multiple countries.
  • 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_69d8279163a081908aec45c0e3f1e02f completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de900a67e08190ab1dcf36e6bb3405 completed April 14, 2026, 7:05 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd551002948190aeb93d245e1449a7 completed May 8, 2026, 3:14 a.m.
Created at: April 10, 2026, 1:16 a.m.