Triple

T13799327
Position Surface form Disambiguated ID Type / Status
Subject Lake Vänern E331596 entity
Predicate hasIsland P970 FINISHED
Object Hammarö
Hammarö is a Swedish island and municipality in Värmland County, known for its forests, coastline, and proximity to the city of Karlstad.
E1086615 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: Hammarö | Statement: [Lake Vänern, hasIsland, Hammarö]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hammarö
Context triple: [Lake Vänern, hasIsland, Hammarö]
  • A. Söderhamn
    Söderhamn is a coastal town in east-central Sweden known for its historical wooden architecture and role as the administrative and commercial center of the surrounding region.
  • B. Värmdö
    Värmdö is a large island and municipality in the Stockholm archipelago of Sweden, known for its coastal landscapes, holiday homes, and proximity to Stockholm.
  • C. Vaxholm
    Vaxholm is a small coastal town and municipality in the Stockholm archipelago of eastern Sweden, known for its historic fortress and picturesque waterfront.
  • D. Sandviken
    Sandviken is an industrial town in central Sweden, best known as the historic home of the steel company Sandvik.
  • E. Fredrikshamn
    Fredrikshamn (Hamina) is a coastal town in southeastern Finland that historically served as an important military and trading center.
  • 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: Hammarö
Triple: [Lake Vänern, hasIsland, Hammarö]
Generated description
Hammarö is a Swedish island and municipality in Värmland County, known for its forests, coastline, and proximity to the city of Karlstad.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Hammarö
Target entity description: Hammarö is a Swedish island and municipality in Värmland County, known for its forests, coastline, and proximity to the city of Karlstad.
  • A. Söderhamn
    Söderhamn is a coastal town in east-central Sweden known for its historical wooden architecture and role as the administrative and commercial center of the surrounding region.
  • B. Värmdö
    Värmdö is a large island and municipality in the Stockholm archipelago of Sweden, known for its coastal landscapes, holiday homes, and proximity to Stockholm.
  • C. Vaxholm
    Vaxholm is a small coastal town and municipality in the Stockholm archipelago of eastern Sweden, known for its historic fortress and picturesque waterfront.
  • D. Sandviken
    Sandviken is an industrial town in central Sweden, best known as the historic home of the steel company Sandvik.
  • E. Fredrikshamn
    Fredrikshamn (Hamina) is a coastal town in southeastern Finland that historically served as an important military and trading center.
  • 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_69d81c58feb08190a77bca8bf7d6d20f completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de025ce9148190b23370f6a522ff7a completed April 14, 2026, 9:01 a.m.
NED1 Entity disambiguation (via context triple) batch_69fd192957008190b525778430b56ca0 completed May 7, 2026, 10:58 p.m.
NEDg Description generation batch_69fd1fb29ef88190bfa15c163ca392ed completed May 7, 2026, 11:26 p.m.
NED2 Entity disambiguation (via description) batch_69fd2006221081908ab46e1eadb52e3d completed May 7, 2026, 11:28 p.m.
Created at: April 9, 2026, 10:11 p.m.