Triple

T3748674
Position Surface form Disambiguated ID Type / Status
Subject Bern E81271 entity
Predicate hasLandmark P105 FINISHED
Object Kornhausbrücke
Kornhausbrücke is a historic bridge in Bern, Switzerland, spanning the Aare River and connecting the Old City with newer districts.
 E391097 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: Kornhausbrücke | Statement: [Bern, hasLandmark, Kornhausbrücke]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Kornhausbrücke
Context triple: [Bern, hasLandmark, Kornhausbrücke]
  • A. Schlossbrücke
    Schlossbrücke is a historic bridge in central Berlin that spans the Spree River, connecting Unter den Linden with Museum Island near the Berlin Palace.
  • B. Rathausbrücke
    Rathausbrücke is a historic pedestrian bridge in central Zurich, Switzerland, spanning the Limmat River near the city hall and the old town.
  • C. Hardbrücke
    Hardbrücke is a major road and railway bridge in Zurich, Switzerland, serving as an important traffic artery across the Limmat and nearby rail tracks.
  • D. Luitpoldbrücke
    Luitpoldbrücke is a historic bridge in Munich that spans the Isar River and connects key parts of the city along Prinzregentenstraße.
  • E. Möckernbrücke
    Möckernbrücke is a Berlin U-Bahn station and major interchange point located near the Landwehr Canal in the Kreuzberg district.
  • 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: Kornhausbrücke
Triple: [Bern, hasLandmark, Kornhausbrücke]
Generated description
Kornhausbrücke is a historic bridge in Bern, Switzerland, spanning the Aare River and connecting the Old City with newer districts.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Kornhausbrücke
Target entity description: Kornhausbrücke is a historic bridge in Bern, Switzerland, spanning the Aare River and connecting the Old City with newer districts.
  • A. Schlossbrücke
    Schlossbrücke is a historic bridge in central Berlin that spans the Spree River, connecting Unter den Linden with Museum Island near the Berlin Palace.
  • B. Rathausbrücke
    Rathausbrücke is a historic pedestrian bridge in central Zurich, Switzerland, spanning the Limmat River near the city hall and the old town.
  • C. Hardbrücke
    Hardbrücke is a major road and railway bridge in Zurich, Switzerland, serving as an important traffic artery across the Limmat and nearby rail tracks.
  • D. Luitpoldbrücke
    Luitpoldbrücke is a historic bridge in Munich that spans the Isar River and connects key parts of the city along Prinzregentenstraße.
  • E. Möckernbrücke
    Möckernbrücke is a Berlin U-Bahn station and major interchange point located near the Landwehr Canal in the Kreuzberg district.
  • 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_69ad8b19b7b08190a6188804e99c53e9 completed March 8, 2026, 2:43 p.m.
NER Named-entity recognition batch_69adcb6bf95c81909796fbc84995ae05 completed March 8, 2026, 7:18 p.m.
NED1 Entity disambiguation (via context triple) batch_69b4fb0c116c8190a74fff15a5de8296 completed March 14, 2026, 6:07 a.m.
NEDg Description generation batch_69b4fe1276f48190aadabac646367fa2 completed March 14, 2026, 6:20 a.m.
NED2 Entity disambiguation (via description) batch_69b4fe683c8081908313bf4a214d2446 completed March 14, 2026, 6:21 a.m.
Created at: March 8, 2026, 3:35 p.m.