Triple

T21294541
Position Surface form Disambiguated ID Type / Status
Subject Erik Bergman E524885 entity
Predicate spouse P13 FINISHED
Object Karin Åkerblom
Karin Åkerblom is known as the spouse of Swedish actor Erik Bergman.
E1477024 NE FINISHED

How this triple was built (4 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: Karin Åkerblom | Statement: [Erik Bergman, spouse, Karin Åkerblom]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Karin Åkerblom
Context triple: [Erik Bergman, spouse, Karin Åkerblom]
  • A. Karin Bergöö
    Karin Bergöö was a Swedish artist and designer best known as the wife and creative collaborator of painter Carl Larsson, whose work and home interiors significantly influenced Scandinavian design.
  • B. Karin Risberg
    Karin Risberg is a notable individual who carries the Swedish surname Risberg, recognized among its prominent bearers.
  • C. Karin Andersson
    Karin Andersson is a notable individual who shares the Swedish surname Andersson and is recognized as one of its prominent bearers.
  • D. Karin Hansson
    Karin Hansson is known primarily as the daughter of Swedish Prime Minister Per Albin Hansson.
  • E. Gunnel Lindblom
    Gunnel Lindblom was a Swedish actress and director best known for her frequent collaborations with filmmaker Ingmar Bergman in both film and theater.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Karin Åkerblom
Triple: [Erik Bergman, spouse, Karin Åkerblom]
Generated description
Karin Åkerblom is known as the spouse of Swedish actor Erik Bergman.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Karin Åkerblom
Target entity description: Karin Åkerblom is known as the spouse of Swedish actor Erik Bergman.
  • A. Karin Bergöö
    Karin Bergöö was a Swedish artist and designer best known as the wife and creative collaborator of painter Carl Larsson, whose work and home interiors significantly influenced Scandinavian design.
  • B. Karin Risberg
    Karin Risberg is a notable individual who carries the Swedish surname Risberg, recognized among its prominent bearers.
  • C. Karin Andersson
    Karin Andersson is a notable individual who shares the Swedish surname Andersson and is recognized as one of its prominent bearers.
  • D. Karin Hansson
    Karin Hansson is known primarily as the daughter of Swedish Prime Minister Per Albin Hansson.
  • E. Gunnel Lindblom
    Gunnel Lindblom was a Swedish actress and director best known for her frequent collaborations with filmmaker Ingmar Bergman in both film and theater.
  • F. None of above. chosen

Provenance (5 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_69e0b517e6748190850d6f6ddf323d69 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e73857784881908c3b8418a4c00c1e completed April 21, 2026, 8:41 a.m.
NED1 Entity disambiguation (via context triple) batch_6a099ecf32888190a3d1e041e96c3a3c completed May 17, 2026, 10:56 a.m.
NEDg Description generation batch_6a099f8c4a5c8190a67b3185fe8a02ad completed May 17, 2026, 10:59 a.m.
NED2 Entity disambiguation (via description) batch_6a099ffeb4b88190b2859b55ba356e22 completed May 17, 2026, 11:01 a.m.
Created at: April 16, 2026, 4:04 p.m.