Triple

T6069676
Position Surface form Disambiguated ID Type / Status
Subject Midtbyen, Trondheim E135247 entity
Predicate contains P35 FINISHED
Object Bakke bru
Bakke bru is a bridge in Trondheim, Norway, connecting the central district of Midtbyen with the Bakklandet neighborhood across the Nidelva river.
 E567382 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: Bakke bru | Statement: [Midtbyen, Trondheim, contains, Bakke bru]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Bakke bru
Context triple: [Midtbyen, Trondheim, contains, Bakke bru]
  • A. Bekkestua
    Bekkestua is a suburban center in Bærum, Norway, functioning as a local commercial and transport hub just west of Oslo.
  • B. Brekstad
    Brekstad is a coastal town in central Norway that serves as an administrative and commercial center for the Fosen region.
  • C. Blakstad
    Blakstad is a village in Agder county, Norway, known as the main local hub for services and administration in the surrounding Froland area.
  • D. Lysgårdsbakken
    Lysgårdsbakken is a large ski jumping hill complex in Lillehammer, Norway, best known for hosting the ski jumping events of the 1994 Winter Olympics.
  • E. Skillebekk
    Skillebekk is a residential neighborhood in Oslo, Norway, known for its central location, historic architecture, and proximity to the Frogner and city center areas.
  • 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: Bakke bru
Triple: [Midtbyen, Trondheim, contains, Bakke bru]
Generated description
Bakke bru is a bridge in Trondheim, Norway, connecting the central district of Midtbyen with the Bakklandet neighborhood across the Nidelva river.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Bakke bru
Target entity description: Bakke bru is a bridge in Trondheim, Norway, connecting the central district of Midtbyen with the Bakklandet neighborhood across the Nidelva river.
  • A. Bekkestua
    Bekkestua is a suburban center in Bærum, Norway, functioning as a local commercial and transport hub just west of Oslo.
  • B. Brekstad
    Brekstad is a coastal town in central Norway that serves as an administrative and commercial center for the Fosen region.
  • C. Blakstad
    Blakstad is a village in Agder county, Norway, known as the main local hub for services and administration in the surrounding Froland area.
  • D. Lysgårdsbakken
    Lysgårdsbakken is a large ski jumping hill complex in Lillehammer, Norway, best known for hosting the ski jumping events of the 1994 Winter Olympics.
  • E. Skillebekk
    Skillebekk is a residential neighborhood in Oslo, Norway, known for its central location, historic architecture, and proximity to the Frogner and city center areas.
  • 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_69c00879e8048190b690717d19c5bc03 completed March 22, 2026, 3:19 p.m.
NER Named-entity recognition batch_69c0574157848190bb8e0972eb55a363 completed March 22, 2026, 8:55 p.m.
NED1 Entity disambiguation (via context triple) batch_69c11d349f288190833384eb9e6c7f52 completed March 23, 2026, 11 a.m.
NEDg Description generation batch_69c11ec11864819084c31d98133ca53a completed March 23, 2026, 11:06 a.m.
NED2 Entity disambiguation (via description) batch_69c11f29842881909acf88a1fa896354 completed March 23, 2026, 11:08 a.m.
Created at: March 22, 2026, 4:10 p.m.