Triple

T15448167
Position Surface form Disambiguated ID Type / Status
Subject Brumunddal E370077 entity
Predicate hasRiver P165 FINISHED
Object Brumunda
Brumunda is a river in Innlandet county, Norway, flowing through the town of Brumunddal before reaching Lake Mjøsa.
E1157163 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: Brumunda | Statement: [Brumunddal, hasRiver, Brumunda]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Brumunda
Context triple: [Brumunddal, hasRiver, Brumunda]
  • A. Breuci
    The Breuci were an ancient Illyrian tribe known for their significant role in resisting Roman rule during major uprisings in the Balkans.
  • B. Bruparck
    Bruparck is a leisure and entertainment complex in Brussels that includes attractions such as theme parks, cinemas, and the miniature park Mini-Europe.
  • C. Frunze
    Frunze is a surname most notably associated with Mikhail Frunze, a prominent Bolshevik leader and Red Army commander during the Russian Civil War.
  • D. Bumba
    Bumba is a Romanian professional footballer known for playing as an attacking midfielder and winger for various clubs in Europe.
  • E. Breng
    Breng is a Dutch public transport operator providing regional bus and train services in and around Arnhem and Nijmegen 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: Brumunda
Triple: [Brumunddal, hasRiver, Brumunda]
Generated description
Brumunda is a river in Innlandet county, Norway, flowing through the town of Brumunddal before reaching Lake Mjøsa.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Brumunda
Target entity description: Brumunda is a river in Innlandet county, Norway, flowing through the town of Brumunddal before reaching Lake Mjøsa.
  • A. Breuci
    The Breuci were an ancient Illyrian tribe known for their significant role in resisting Roman rule during major uprisings in the Balkans.
  • B. Bruparck
    Bruparck is a leisure and entertainment complex in Brussels that includes attractions such as theme parks, cinemas, and the miniature park Mini-Europe.
  • C. Frunze
    Frunze is a surname most notably associated with Mikhail Frunze, a prominent Bolshevik leader and Red Army commander during the Russian Civil War.
  • D. Bumba
    Bumba is a Romanian professional footballer known for playing as an attacking midfielder and winger for various clubs in Europe.
  • E. Breng
    Breng is a Dutch public transport operator providing regional bus and train services in and around Arnhem and Nijmegen 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_69d85a19180081909925012fbf4e62a3 completed April 10, 2026, 2:02 a.m.
NER Named-entity recognition batch_69e03ef767b4819099f2c0919a158321 completed April 16, 2026, 1:44 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff21afb6f4819094162ca842b7eb60 completed May 9, 2026, 11:59 a.m.
NEDg Description generation batch_69ff22a9429081909724f248da07e24a completed May 9, 2026, 12:03 p.m.
NED2 Entity disambiguation (via description) batch_69ff2339ae808190bf2d4676215399c0 completed May 9, 2026, 12:06 p.m.
Created at: April 10, 2026, 3:21 a.m.