Triple

T5789050
Position Surface form Disambiguated ID Type / Status
Subject Queen Sonja of Norway E128345 entity
Predicate father P120 FINISHED
Object Karl August Haraldsen E535976 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: Karl August Haraldsen | Statement: [Queen Sonja of Norway, father, Karl August Haraldsen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Karl August Haraldsen
Context triple: [Queen Sonja of Norway, father, Karl August Haraldsen]
  • A. Karl August Haraldsen chosen
    Karl August Haraldsen was a Norwegian clothing merchant best known as the father of Queen Sonja of Norway.
  • B. Peder Ristvedt
    Peder Ristvedt was a Norwegian polar explorer and engineer who took part in Roald Amundsen’s historic early 20th-century Arctic voyages.
  • C. Johann Olav Koss
    Johann Olav Koss is a Norwegian speed skater renowned for winning multiple gold medals and setting world records at the 1994 Lillehammer Winter Olympics.
  • D. Arvid Bjerke
    Arvid Bjerke was a Swedish architect known for his significant contributions to early 20th-century architecture in Gothenburg.
  • E. Kjartan Fløgstad
    Kjartan Fløgstad is a Norwegian author known for his socially engaged, linguistically inventive novels and essays that explore industrialization, class, and cultural change in Norway.
  • 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_69c0084450048190bc647b649a05136b completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c02a53d0148190bdebc4f5609939ac completed March 22, 2026, 5:43 p.m.
NED1 Entity disambiguation (via context triple) batch_69c107dc9a2481908474defa2c849595 completed March 23, 2026, 9:29 a.m.
Created at: March 22, 2026, 3:51 p.m.