Triple

T20018420
Position Surface form Disambiguated ID Type / Status
Subject Sande (Møre og Romsdal) E494782 entity
Predicate hasIsland P970 FINISHED
Object Voksa
Voksa is a small Norwegian island located in Sande Municipality in Møre og Romsdal county, known for its coastal landscape and rural character.
E1407195 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: Voksa | Statement: [Sande (Møre og Romsdal), hasIsland, Voksa]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Voksa
Context triple: [Sande (Møre og Romsdal), hasIsland, Voksa]
  • A. Vawkavisk
    Vawkavisk is a town in western Belarus known for its long history dating back to medieval times and its role as a regional cultural and economic center.
  • B. Võsu
    Võsu is a small coastal settlement in northern Estonia known for its sandy beach and role as a popular summer resort.
  • C. Vosso
    Vosso is a river in western Norway known for flowing through Voss municipality and contributing to the region’s scenic fjord landscape.
  • D. Vrély
    Vrély is a small rural commune in the Somme department of northern France.
  • E. Veele
    Veele is a small village in the municipality of Vlagtwedde in the province of Groningen in the Netherlands.
  • 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: Voksa
Triple: [Sande (Møre og Romsdal), hasIsland, Voksa]
Generated description
Voksa is a small Norwegian island located in Sande Municipality in Møre og Romsdal county, known for its coastal landscape and rural character.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Voksa
Target entity description: Voksa is a small Norwegian island located in Sande Municipality in Møre og Romsdal county, known for its coastal landscape and rural character.
  • A. Vawkavisk
    Vawkavisk is a town in western Belarus known for its long history dating back to medieval times and its role as a regional cultural and economic center.
  • B. Võsu
    Võsu is a small coastal settlement in northern Estonia known for its sandy beach and role as a popular summer resort.
  • C. Vosso
    Vosso is a river in western Norway known for flowing through Voss municipality and contributing to the region’s scenic fjord landscape.
  • D. Vrély
    Vrély is a small rural commune in the Somme department of northern France.
  • E. Veele
    Veele is a small village in the municipality of Vlagtwedde in the province of Groningen in the Netherlands.
  • 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_69da626bfd288190aa5d65098b6433ae completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e6623e40748190b1abb0ead9acab4e completed April 20, 2026, 5:28 p.m.
NED1 Entity disambiguation (via context triple) batch_6a080e286230819097e564d028e73ab5 completed May 16, 2026, 6:26 a.m.
NEDg Description generation batch_6a080ef87f08819091b4a76009b1c4ba completed May 16, 2026, 6:30 a.m.
NED2 Entity disambiguation (via description) batch_6a080f8bb81c819098d39ad6e1642aa8 completed May 16, 2026, 6:32 a.m.
Created at: April 11, 2026, 3:34 p.m.