Triple

T19414467
Position Surface form Disambiguated ID Type / Status
Subject Bern Old Town E485671 entity
Predicate hasPart P35 FINISHED
Object Münster of Bern NE NERFINISHED

How this triple was built (3 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: Münster of Bern | Statement: [Bern Old Town, hasPart, Münster of Bern]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Münster of Bern
Context triple: [Bern Old Town, hasPart, Münster of Bern]
  • A. Old Town of Bern
    The Old Town of Bern is a well-preserved medieval city center and UNESCO World Heritage Site in Switzerland, known for its arcaded streets, sandstone buildings, and historic landmarks along a loop of the Aare River.
  • B. Murten Castle
    Murten Castle is a historic medieval fortress in the Swiss town of Murten, notable for its well-preserved architecture and role in the region’s defensive history.
  • C. Neuenburg Castle
    Neuenburg Castle is a medieval hilltop fortress in central Germany, notable for its well-preserved Romanesque architecture and historical role in regional power and defense.
  • D. Schloss Münster
    Schloss Münster is a baroque palace in Münster, Germany, now primarily used as the main administrative building of the University of Münster.
  • E. Rapperswil Castle
    Rapperswil Castle is a medieval hilltop fortress in the Swiss town of Rapperswil, overlooking Lake Zurich and known for its well-preserved architecture and scenic views.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Münster of Bern
Target entity description: The Münster of Bern is a prominent late Gothic cathedral in Switzerland’s capital, renowned for its towering spire and richly decorated portal.
  • A. Old Town of Bern
    The Old Town of Bern is a well-preserved medieval city center and UNESCO World Heritage Site in Switzerland, known for its arcaded streets, sandstone buildings, and historic landmarks along a loop of the Aare River.
  • B. Murten Castle
    Murten Castle is a historic medieval fortress in the Swiss town of Murten, notable for its well-preserved architecture and role in the region’s defensive history.
  • C. Neuenburg Castle
    Neuenburg Castle is a medieval hilltop fortress in central Germany, notable for its well-preserved Romanesque architecture and historical role in regional power and defense.
  • D. Schloss Münster
    Schloss Münster is a baroque palace in Münster, Germany, now primarily used as the main administrative building of the University of Münster.
  • E. Rapperswil Castle
    Rapperswil Castle is a medieval hilltop fortress in the Swiss town of Rapperswil, overlooking Lake Zurich and known for its well-preserved architecture and scenic views.
  • F. None of above. chosen

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_69d8e8d688f881909c85104a62e09d8a completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e62af834fc81908cb176076de10c1c completed April 20, 2026, 1:32 p.m.
Created at: April 10, 2026, 1:37 p.m.