Triple

T20725966
Position Surface form Disambiguated ID Type / Status
Subject Kornhausbrücke E509435 entity
Predicate hasNameInLanguage P15 FINISHED
Object Kornhausbrücke (German) NE NERFINISHED

How this triple was built (2 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 (German) | Statement: [Kornhausbrücke, hasNameInLanguage, Kornhausbrücke (German)]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kornhausbrücke (German)
Context triple: [Kornhausbrücke, hasNameInLanguage, Kornhausbrücke (German)]
  • A. Kornhausbrücke chosen
    Kornhausbrücke is a historic bridge in Bern, Switzerland, spanning the Aare River and connecting the Old City with newer districts.
  • B. Kornhausbrücke
    Kornhausbrücke is a bridge in Zurich, Switzerland, that carries traffic across the Limmat River near the city’s historic center.
  • C. Boschbrücke
    Boschbrücke is a bridge in Munich, Germany, that connects to the Museumsinsel (Museum Island) over the Isar River.
  • D. Krämerbrücke
    Krämerbrücke is a historic medieval bridge in Erfurt, Germany, famous for its densely packed, half-timbered houses built along its span and its role as a former merchants’ street.
  • E. Knesebeck Bridge
    Knesebeck Bridge is a bridge spanning the Teltow Canal in Berlin, Germany, serving as a local road and pedestrian crossing.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e0b4c4cc648190b45fda6e2b20af56 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c1e7aabc819084f9e9fd45e877fd completed April 21, 2026, 12:16 a.m.
Created at: April 16, 2026, 12:29 p.m.