Triple

T18169480
Position Surface form Disambiguated ID Type / Status
Subject Östen Undén E434983 entity
Predicate familyName P18 FINISHED
Object Undén
Undén is a Swedish surname most notably associated with Östen Undén, a prominent 20th-century Swedish politician and jurist.
E1310034 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: Undén | Statement: [Östen Undén, familyName, Undén]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Undén
Context triple: [Östen Undén, familyName, Undén]
  • A. Oudenaken
    Oudenaken is a small village in the Flemish Brabant province of Belgium, forming part of the municipality of Sint-Pieters-Leeuw.
  • B. Unnan
    Unnan is a city in Shimane Prefecture, Japan, known for its rural landscapes, hot springs, and traditional cultural sites.
  • C. Unten
    Unten is a small coastal settlement on Izena Island in Okinawa Prefecture, Japan.
  • D. Uden
    Uden is a town in the southern Netherlands known for its location in the province of North Brabant and its proximity to nature reserves and regional industry.
  • E. Autan
    Autan is an insect repellent brand owned by SC Johnson & Son, known for products that protect against mosquito and other insect bites.
  • 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: Undén
Triple: [Östen Undén, familyName, Undén]
Generated description
Undén is a Swedish surname most notably associated with Östen Undén, a prominent 20th-century Swedish politician and jurist.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Undén
Target entity description: Undén is a Swedish surname most notably associated with Östen Undén, a prominent 20th-century Swedish politician and jurist.
  • A. Oudenaken
    Oudenaken is a small village in the Flemish Brabant province of Belgium, forming part of the municipality of Sint-Pieters-Leeuw.
  • B. Unnan
    Unnan is a city in Shimane Prefecture, Japan, known for its rural landscapes, hot springs, and traditional cultural sites.
  • C. Unten
    Unten is a small coastal settlement on Izena Island in Okinawa Prefecture, Japan.
  • D. Uden
    Uden is a town in the southern Netherlands known for its location in the province of North Brabant and its proximity to nature reserves and regional industry.
  • E. Autan
    Autan is an insect repellent brand owned by SC Johnson & Son, known for products that protect against mosquito and other insect bites.
  • 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_69d8b90b7a188190b3fc7b8d4a6cd20a completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4df53ef148190a32aad0253547645 completed April 19, 2026, 1:57 p.m.
NED1 Entity disambiguation (via context triple) batch_6a038fc6c5008190a5ade67801d6df75 completed May 12, 2026, 8:38 p.m.
NEDg Description generation batch_6a03914c5f6081908963548dc01a524a completed May 12, 2026, 8:45 p.m.
NED2 Entity disambiguation (via description) batch_6a03925c322081909d435251e869194d completed May 12, 2026, 8:49 p.m.
Created at: April 10, 2026, 10:30 a.m.