Triple

T4434696
Position Surface form Disambiguated ID Type / Status
Subject Jotunheimen E95619 entity
Predicate hasGlacier P4580 FINISHED
Object Uranosbreen
Uranosbreen is a glacier located in the Jotunheimen mountain range of Norway, known for its high-altitude alpine environment.
E442471 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: Uranosbreen | Statement: [Jotunheimen, hasGlacier, Uranosbreen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Uranosbreen
Context triple: [Jotunheimen, hasGlacier, Uranosbreen]
  • A. Svellnosbreen
    Svellnosbreen is a notable glacier in the Jotunheimen mountain range of Norway, situated near the country’s highest peak, Galdhøpiggen.
  • B. Okstindbreen
    Okstindbreen is a glacier located on and around the Oksskolten massif in northern Norway.
  • C. Styggebreen
    Styggebreen is a glacier in Norway’s Jotunheimen mountains, known for lying close to Galdhøpiggen, the country’s highest peak.
  • D. Gunnbjørn Fjeld
    Gunnbjørn Fjeld is the tallest mountain in the Arctic and a prominent peak of Greenland’s remote ice-covered interior.
  • E. Stetind
    Stetind is a distinctive, obelisk-shaped granite mountain in Nordland, Norway, often called Norway’s national mountain and renowned among climbers and photographers.
  • 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: Uranosbreen
Triple: [Jotunheimen, hasGlacier, Uranosbreen]
Generated description
Uranosbreen is a glacier located in the Jotunheimen mountain range of Norway, known for its high-altitude alpine environment.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Uranosbreen
Target entity description: Uranosbreen is a glacier located in the Jotunheimen mountain range of Norway, known for its high-altitude alpine environment.
  • A. Svellnosbreen
    Svellnosbreen is a notable glacier in the Jotunheimen mountain range of Norway, situated near the country’s highest peak, Galdhøpiggen.
  • B. Okstindbreen
    Okstindbreen is a glacier located on and around the Oksskolten massif in northern Norway.
  • C. Styggebreen
    Styggebreen is a glacier in Norway’s Jotunheimen mountains, known for lying close to Galdhøpiggen, the country’s highest peak.
  • D. Gunnbjørn Fjeld
    Gunnbjørn Fjeld is the tallest mountain in the Arctic and a prominent peak of Greenland’s remote ice-covered interior.
  • E. Stetind
    Stetind is a distinctive, obelisk-shaped granite mountain in Nordland, Norway, often called Norway’s national mountain and renowned among climbers and photographers.
  • 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_69b3453ea2b48190a26f154b3b8fece5 completed March 12, 2026, 10:59 p.m.
NER Named-entity recognition batch_69b35588e99881908fea7b71a33e2bb6 completed March 13, 2026, 12:08 a.m.
NED1 Entity disambiguation (via context triple) batch_69b628002e208190a68c659abd348040 completed March 15, 2026, 3:31 a.m.
NEDg Description generation batch_69b628ffed1c819097d048712e9aafef completed March 15, 2026, 3:35 a.m.
NED2 Entity disambiguation (via description) batch_69b6298d1ff88190a58a6fc5992ef864 completed March 15, 2026, 3:37 a.m.
Created at: March 12, 2026, 11:31 p.m.