Triple
T7725208
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Stig Anderson |
E175111
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object |
Gudrun Rydstedt
Gudrun Rydstedt was the wife of Swedish music executive and ABBA manager Stig Anderson.
|
E688334
|
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: Gudrun Rydstedt | Statement: [Stig Anderson, spouse, Gudrun Rydstedt]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gudrun Rydstedt Context triple: [Stig Anderson, spouse, Gudrun Rydstedt]
-
A.
Ingerid Vilberg
Ingerid Vilberg was the wife of renowned Norwegian sculptor Gustav Vigeland.
-
B.
Maud Runnström
Maud Runnström was the wife of Swedish physicist and Nobel laureate Kai Siegbahn.
-
C.
Signe Hammarsten-Jansson
Signe Hammarsten-Jansson was a Swedish-Finnish illustrator and graphic artist best known as the mother of Moomin creator Tove Jansson and for her influential work in Finnish stamp and book illustration.
-
D.
Hjördis Genberg
Hjördis Genberg was a Swedish fashion model and actress best known for her long and high-profile marriage to British actor David Niven.
-
E.
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."
- 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: Gudrun Rydstedt Triple: [Stig Anderson, spouse, Gudrun Rydstedt]
Generated description
Gudrun Rydstedt was the wife of Swedish music executive and ABBA manager Stig Anderson.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Gudrun Rydstedt Target entity description: Gudrun Rydstedt was the wife of Swedish music executive and ABBA manager Stig Anderson.
-
A.
Ingerid Vilberg
Ingerid Vilberg was the wife of renowned Norwegian sculptor Gustav Vigeland.
-
B.
Maud Runnström
Maud Runnström was the wife of Swedish physicist and Nobel laureate Kai Siegbahn.
-
C.
Signe Hammarsten-Jansson
Signe Hammarsten-Jansson was a Swedish-Finnish illustrator and graphic artist best known as the mother of Moomin creator Tove Jansson and for her influential work in Finnish stamp and book illustration.
-
D.
Hjördis Genberg
Hjördis Genberg was a Swedish fashion model and actress best known for her long and high-profile marriage to British actor David Niven.
-
E.
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."
- 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_69c6995d541c81909eaa646b1a8369a9 |
completed | March 27, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69c7031394e48190833b906af9166fe5 |
completed | March 27, 2026, 10:22 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c8d6b1f7648190a0e2fd82ecb9c8b9 |
completed | March 29, 2026, 7:37 a.m. |
| NEDg | Description generation | batch_69c8d73968ec81908586ccdf4118db56 |
completed | March 29, 2026, 7:39 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69c8d825d3fc8190a98879a4790aafcd |
completed | March 29, 2026, 7:43 a.m. |
Created at: March 27, 2026, 4:05 p.m.