Triple

T3506361
Position Surface form Disambiguated ID Type / Status
Subject Sognefjord E74083 entity
Predicate hasTownOnShore P969 FINISHED
Object Lærdalsøyri
Lærdalsøyri is a historic village in western Norway known for its well-preserved wooden buildings and location at the inner end of the Sognefjord.
 E363659 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: Lærdalsøyri | Statement: [Sognefjord, hasTownOnShore, Lærdalsøyri]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Lærdalsøyri
Context triple: [Sognefjord, hasTownOnShore, Lærdalsøyri]
  • A. Hynnekleiv
    Hynnekleiv is a small village in the municipality of Froland in Agder county, southern Norway.
  • B. Fugloy
    Fugloy is a small, remote island in the northeastern Faroe Islands, known for its dramatic cliffs, rich birdlife, and traditional village life.
  • C. Dæhlie
    Dæhlie is a Norwegian surname most famously associated with legendary cross-country skier Bjørn Dæhlie.
  • D. Fløya
    Fløya is a Norwegian women's football club based in Tromsø that competes in the country's league system.
  • E. Gryllefjord
    Gryllefjord is a small coastal fishing village located on the island of Senja in northern Norway.
  • 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: Lærdalsøyri
Triple: [Sognefjord, hasTownOnShore, Lærdalsøyri]
Generated description
Lærdalsøyri is a historic village in western Norway known for its well-preserved wooden buildings and location at the inner end of the Sognefjord.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Lærdalsøyri
Target entity description: Lærdalsøyri is a historic village in western Norway known for its well-preserved wooden buildings and location at the inner end of the Sognefjord.
  • A. Hynnekleiv
    Hynnekleiv is a small village in the municipality of Froland in Agder county, southern Norway.
  • B. Fugloy
    Fugloy is a small, remote island in the northeastern Faroe Islands, known for its dramatic cliffs, rich birdlife, and traditional village life.
  • C. Dæhlie
    Dæhlie is a Norwegian surname most famously associated with legendary cross-country skier Bjørn Dæhlie.
  • D. Fløya
    Fløya is a Norwegian women's football club based in Tromsø that competes in the country's league system.
  • E. Gryllefjord
    Gryllefjord is a small coastal fishing village located on the island of Senja in northern Norway.
  • 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_69ad85ce7a9c81909ddc5cf0cb67a6e3 completed March 8, 2026, 2:21 p.m.
NER Named-entity recognition batch_69adbbf52bd8819085a2ac5f48cc5c68 completed March 8, 2026, 6:12 p.m.
NED1 Entity disambiguation (via context triple) batch_69b373e0dc7881909af631182970d132 completed March 13, 2026, 2:18 a.m.
NEDg Description generation batch_69b375337e6c8190a3d2a1561c133ecb completed March 13, 2026, 2:23 a.m.
NED2 Entity disambiguation (via description) batch_69b375bb3f8c819097b295a2881b3b82 completed March 13, 2026, 2:26 a.m.
Created at: March 8, 2026, 3:18 p.m.