Triple

T3882307
Position Surface form Disambiguated ID Type / Status
Subject Galdhøpiggen E92852 entity
Predicate hasNearbyGlacier P43465 FINISHED
Object Svellnosbreen
Svellnosbreen is a notable glacier in the Jotunheimen mountain range of Norway, situated near the country’s highest peak, Galdhøpiggen.
 E394795 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: Svellnosbreen | Statement: [Galdhøpiggen, hasNearbyGlacier, Svellnosbreen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Svellnosbreen
Context triple: [Galdhøpiggen, hasNearbyGlacier, Svellnosbreen]
  • A. Kolåstinden
    Kolåstinden is a prominent alpine peak in Norway’s Sunnmøre Alps, renowned among hikers and ski mountaineers for its steep slopes and panoramic fjord views.
  • B. Skogsvåg
    Skogsvåg is a small coastal village in western Norway, located on the island of Sotra in Vestland county.
  • C. Rondane
    Rondane is a mountainous national park in central Norway known for its high peaks, alpine plateaus, and rich wildlife, including wild reindeer.
  • D. Hodnefjell
    Hodnefjell is an island that forms part of the Finnøy archipelago in Norway.
  • E. Hafjell
    Hafjell is a major Norwegian ski resort in the Øyer municipality, known for hosting alpine events during the 1994 Lillehammer Winter Olympics and offering extensive slopes and winter sports facilities.
  • 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: Svellnosbreen
Triple: [Galdhøpiggen, hasNearbyGlacier, Svellnosbreen]
Generated description
Svellnosbreen is a notable glacier in the Jotunheimen mountain range of Norway, situated near the country’s highest peak, Galdhøpiggen.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Svellnosbreen
Target entity description: Svellnosbreen is a notable glacier in the Jotunheimen mountain range of Norway, situated near the country’s highest peak, Galdhøpiggen.
  • A. Kolåstinden
    Kolåstinden is a prominent alpine peak in Norway’s Sunnmøre Alps, renowned among hikers and ski mountaineers for its steep slopes and panoramic fjord views.
  • B. Skogsvåg
    Skogsvåg is a small coastal village in western Norway, located on the island of Sotra in Vestland county.
  • C. Rondane
    Rondane is a mountainous national park in central Norway known for its high peaks, alpine plateaus, and rich wildlife, including wild reindeer.
  • D. Hodnefjell
    Hodnefjell is an island that forms part of the Finnøy archipelago in Norway.
  • E. Hafjell
    Hafjell is a major Norwegian ski resort in the Øyer municipality, known for hosting alpine events during the 1994 Lillehammer Winter Olympics and offering extensive slopes and winter sports facilities.
  • 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_69aed9697de0819087c2559295ff3d12 completed March 9, 2026, 2:30 p.m.
NER Named-entity recognition batch_69aeec8e8b3481909617ca0e37f8a6d4 completed March 9, 2026, 3:51 p.m.
NED1 Entity disambiguation (via context triple) batch_69b512594fa081909ba2afad11f6ea59 completed March 14, 2026, 7:46 a.m.
NEDg Description generation batch_69b513013db481908f8fb5f56470c0d0 completed March 14, 2026, 7:49 a.m.
NED2 Entity disambiguation (via description) batch_69b5137200a08190bd2a78398e03803e completed March 14, 2026, 7:51 a.m.
Created at: March 9, 2026, 3:20 p.m.