Triple

T7685712
Position Surface form Disambiguated ID Type / Status
Subject Kai Siegbahn E174109 entity
Predicate spouse P13 FINISHED
Object Maud Runnström
Maud Runnström was the wife of Swedish physicist and Nobel laureate Kai Siegbahn.
 E685115 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: Maud Runnström | Statement: [Kai Siegbahn, spouse, Maud Runnström]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Maud Runnström
Context triple: [Kai Siegbahn, spouse, Maud Runnström]
  • A. Ellen Lundström
    Ellen Lundström was the first wife of renowned Swedish film director Ingmar Bergman, with whom he had several children before their divorce.
  • B. Annette Ekblom
    Annette Ekblom is an English actress known for her work in television, film, and theatre, including roles in series such as "Brookside" and "The Broker's Man."
  • C. Marianne Dahlbäck
    Marianne Dahlbäck is a Swedish architect best known for co-designing Stockholm’s Vasa Museum, one of Scandinavia’s most visited cultural landmarks.
  • D. Åsa Wikforss
    Åsa Wikforss is a Swedish philosopher and professor known for her work in philosophy of language and epistemology, as well as for her public engagement in debates on knowledge and democracy.
  • E. Sylvia Ingemarsson
    Sylvia Ingemarsson is a film editor best known for her work on Ingmar Bergman’s drama "Autumn Sonata."
  • 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: Maud Runnström
Triple: [Kai Siegbahn, spouse, Maud Runnström]
Generated description
Maud Runnström was the wife of Swedish physicist and Nobel laureate Kai Siegbahn.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Maud Runnström
Target entity description: Maud Runnström was the wife of Swedish physicist and Nobel laureate Kai Siegbahn.
  • A. Ellen Lundström
    Ellen Lundström was the first wife of renowned Swedish film director Ingmar Bergman, with whom he had several children before their divorce.
  • B. Annette Ekblom
    Annette Ekblom is an English actress known for her work in television, film, and theatre, including roles in series such as "Brookside" and "The Broker's Man."
  • C. Marianne Dahlbäck
    Marianne Dahlbäck is a Swedish architect best known for co-designing Stockholm’s Vasa Museum, one of Scandinavia’s most visited cultural landmarks.
  • D. Åsa Wikforss
    Åsa Wikforss is a Swedish philosopher and professor known for her work in philosophy of language and epistemology, as well as for her public engagement in debates on knowledge and democracy.
  • E. Sylvia Ingemarsson
    Sylvia Ingemarsson is a film editor best known for her work on Ingmar Bergman’s drama "Autumn Sonata."
  • 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_69c6995840408190a19de6c51090f46f completed March 27, 2026, 2:51 p.m.
NER Named-entity recognition batch_69c7022118908190a3a93cfda79be0a4 completed March 27, 2026, 10:18 p.m.
NED1 Entity disambiguation (via context triple) batch_69c8b4fda81881908144cebdd2696e63 completed March 29, 2026, 5:13 a.m.
NEDg Description generation batch_69c8b5a1f758819086f4f4a2b6221369 completed March 29, 2026, 5:16 a.m.
NED2 Entity disambiguation (via description) batch_69c8b649e91c8190b18f8caacb584327 completed March 29, 2026, 5:19 a.m.
Created at: March 27, 2026, 4:02 p.m.