Triple

T16242846
Position Surface form Disambiguated ID Type / Status
Subject Askøy E394295 entity
Predicate hasIsland P970 FINISHED
Object Kollevåg
Kollevåg is a coastal area and recreational spot on the island of Askøy in western Norway, known for its beaches and outdoor activities near Bergen.
E1219124 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: Kollevåg | Statement: [Askøy, hasIsland, Kollevåg]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kollevåg
Context triple: [Askøy, hasIsland, Kollevåg]
  • A. Vikevåg
    Vikevåg is a village in Rogaland county, Norway, known for its coastal setting and role in local administration and services.
  • B. Tveitevåg
    Tveitevåg is a small coastal village in western Norway, located on the island of Askøy in Vestland county.
  • C. Kalvåg
    Kalvåg is a coastal fishing village in Bremanger Municipality in Vestland county, Norway, known for its well-preserved wooden waterfront buildings and maritime heritage.
  • D. Sagvåg
    Sagvåg is a village on the island municipality of Stord in Vestland county, Norway, known for its coastal setting and local maritime industry.
  • E. Kjerknesvågen
    Kjerknesvågen is a small coastal village in the municipality of Inderøy in Trøndelag county, Norway, known for its scenic fjordside setting and rural character.
  • 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: Kollevåg
Triple: [Askøy, hasIsland, Kollevåg]
Generated description
Kollevåg is a coastal area and recreational spot on the island of Askøy in western Norway, known for its beaches and outdoor activities near Bergen.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Kollevåg
Target entity description: Kollevåg is a coastal area and recreational spot on the island of Askøy in western Norway, known for its beaches and outdoor activities near Bergen.
  • A. Vikevåg
    Vikevåg is a village in Rogaland county, Norway, known for its coastal setting and role in local administration and services.
  • B. Tveitevåg chosen
    Tveitevåg is a small coastal village in western Norway, located on the island of Askøy in Vestland county.
  • C. Kalvåg
    Kalvåg is a coastal fishing village in Bremanger Municipality in Vestland county, Norway, known for its well-preserved wooden waterfront buildings and maritime heritage.
  • D. Sagvåg
    Sagvåg is a village on the island municipality of Stord in Vestland county, Norway, known for its coastal setting and local maritime industry.
  • E. Kjerknesvågen
    Kjerknesvågen is a small coastal village in the municipality of Inderøy in Trøndelag county, Norway, known for its scenic fjordside setting and rural character.
  • F. None of above.

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_69d87f2171208190951025e526947816 completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e24560060c8190ace4f4c0bd0d886d completed April 17, 2026, 2:36 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0075856f1881908548579b241e8009 completed May 10, 2026, 12:09 p.m.
NEDg Description generation batch_6a0079bf50dc8190a20057ef8a738e1d completed May 10, 2026, 12:27 p.m.
NED2 Entity disambiguation (via description) batch_6a007a34b42081908a77a3913c40377f completed May 10, 2026, 12:29 p.m.
Created at: April 10, 2026, 5:04 a.m.