Triple

T22333670
Position Surface form Disambiguated ID Type / Status
Subject Viskan E552087 entity
Predicate mouthLocatedIn P417 FINISHED
Object Frillesås
Frillesås is a locality on Sweden’s west coast in Halland County, known for its coastal setting and proximity to the river Viskan’s outlet into the Kattegat.
 E1530533 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: Frillesås | Statement: [Viskan, mouthLocatedIn, Frillesås]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Frillesås
Context triple: [Viskan, mouthLocatedIn, Frillesås]
  • A. Lauvåsen
    Lauvåsen is a hill that forms the highest elevation on the island of Tromøya in southern Norway.
  • B. Lauvåsen
    Lauvåsen is an island that forms part of the Flekkerøy archipelago in southern Norway.
  • C. Fagersjö
    Fagersjö is a residential district in southern Stockholm, Sweden, known for its proximity to lakes and green areas.
  • D. Såtenäs
    Såtenäs is a locality in western Sweden best known as a major Swedish Air Force base and home of the F 7 Wing.
  • E. Fåberg
    Fåberg is a village and former municipality in Innlandet county, Norway, situated near Lillehammer in the Gudbrandsdalen valley.
  • 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: Frillesås
Triple: [Viskan, mouthLocatedIn, Frillesås]
Generated description
Frillesås is a locality on Sweden’s west coast in Halland County, known for its coastal setting and proximity to the river Viskan’s outlet into the Kattegat.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Frillesås
Target entity description: Frillesås is a locality on Sweden’s west coast in Halland County, known for its coastal setting and proximity to the river Viskan’s outlet into the Kattegat.
  • A. Lauvåsen
    Lauvåsen is an island that forms part of the Flekkerøy archipelago in southern Norway.
  • B. Lauvåsen
    Lauvåsen is a hill that forms the highest elevation on the island of Tromøya in southern Norway.
  • C. Fagersjö
    Fagersjö is a residential district in southern Stockholm, Sweden, known for its proximity to lakes and green areas.
  • D. Såtenäs
    Såtenäs is a locality in western Sweden best known as a major Swedish Air Force base and home of the F 7 Wing.
  • E. Fåberg
    Fåberg is a village and former municipality in Innlandet county, Norway, situated near Lillehammer in the Gudbrandsdalen valley.
  • 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_69e11e482f788190b78d1588fc26d606 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f1577cdcb08190a760e195c1051adb completed April 29, 2026, 12:57 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0ad529a9b081908edf8eedee7e957c completed May 18, 2026, 9 a.m.
NEDg Description generation batch_6a0ad993b9188190aacf482038b3cd29 completed May 18, 2026, 9:19 a.m.
NED2 Entity disambiguation (via description) batch_6a0ada0cef848190864a88d7baa24a81 completed May 18, 2026, 9:21 a.m.
Created at: April 16, 2026, 8:43 p.m.