Triple

T20536018
Position Surface form Disambiguated ID Type / Status
Subject Romsdalen E504200 entity
Predicate hasMountain P10602 FINISHED
Object Kongen
Kongen is a prominent mountain peak in Norway’s Romsdalen valley, known for its striking alpine profile and popular climbing routes.
 E1437897 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: Kongen | Statement: [Romsdalen, hasMountain, Kongen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Kongen
Context triple: [Romsdalen, hasMountain, Kongen]
  • A. Kœnig
    Kœnig is a French surname most notably associated with figures such as General Marie-Pierre Kœnig, a prominent military leader during World War II.
  • B. König
    König is a German-language surname borne by numerous individuals, including notable figures in fields such as religion, science, and the arts.
  • C. Koning
    Koning is a Dutch surname and term meaning “king,” commonly used in the Netherlands and Belgium.
  • D. Kingo
    Kingo is an Eternal who lives on Earth as a charismatic Bollywood movie star while secretly using his cosmic powers to protect humanity.
  • E. Kingo
    Kingo is a Japanese given name most notably borne by Tatsuno Kingo, a prominent architect of Japan’s Meiji era.
  • 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: Kongen
Triple: [Romsdalen, hasMountain, Kongen]
Generated description
Kongen is a prominent mountain peak in Norway’s Romsdalen valley, known for its striking alpine profile and popular climbing routes.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Kongen
Target entity description: Kongen is a prominent mountain peak in Norway’s Romsdalen valley, known for its striking alpine profile and popular climbing routes.
  • A. Kœnig
    Kœnig is a French surname most notably associated with figures such as General Marie-Pierre Kœnig, a prominent military leader during World War II.
  • B. König
    König is a German-language surname borne by numerous individuals, including notable figures in fields such as religion, science, and the arts.
  • C. Koning
    Koning is a Dutch surname and term meaning “king,” commonly used in the Netherlands and Belgium.
  • D. Kingo
    Kingo is an Eternal who lives on Earth as a charismatic Bollywood movie star while secretly using his cosmic powers to protect humanity.
  • E. Kingo
    Kingo is a Japanese given name most notably borne by Tatsuno Kingo, a prominent architect of Japan’s Meiji era.
  • 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_69e0b4b476648190bc6019622ae54d3c completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6a06ed3088190bd01a95672b01ad6 completed April 20, 2026, 9:53 p.m.
NED1 Entity disambiguation (via context triple) batch_6a08a5638f688190b74c79fcb506a24d completed May 16, 2026, 5:12 p.m.
NEDg Description generation batch_6a08a9459444819089c180ede20cc100 completed May 16, 2026, 5:28 p.m.
NED2 Entity disambiguation (via description) batch_6a08a9c8ae4c8190951fb838bd8c5e91 completed May 16, 2026, 5:30 p.m.
Created at: April 16, 2026, 11:37 a.m.