Triple

T790605
Position Surface form Disambiguated ID Type / Status
Subject Jura E16904 entity
Predicate bordersCanton P224 FINISHED
Object Bern E18380 NE FINISHED

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: Bern | Statement: [Jura, bordersCanton, Bern]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bern
Context triple: [Jura, bordersCanton, Bern]
  • A. Bern chosen
    Bern is the capital city of Switzerland, known for its well-preserved medieval old town and role as a political and cultural center.
  • B. Canton
    Canton is the historical Western name for Guangzhou, a major port city in southern China and the capital of Guangdong province.
  • C. Rochester
    Rochester is a major city in western New York State known historically for its role in industry, photography, and social reform movements.
  • D. Burlington
    Burlington is a historic city in present-day New Jersey that once served as the colonial capital of the Province of New Jersey.
  • E. Burlington
    Burlington is a suburban town in Massachusetts known for its proximity to Boston and its mix of residential neighborhoods, office parks, and retail centers.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69a4936cb7448190914f5fe4b8d81607 completed March 1, 2026, 7:28 p.m.
NER Named-entity recognition batch_69a4a79754988190ab494b1c54d6a2a4 completed March 1, 2026, 8:54 p.m.
NED1 Entity disambiguation (via context triple) batch_69ac16f56bc0819094085d61f1f29f70 completed March 7, 2026, 12:15 p.m.
Created at: March 1, 2026, 7:38 p.m.