Triple

T18597546
Position Surface form Disambiguated ID Type / Status
Subject Midttrafik E454531 entity
Predicate operatesIn P82 FINISHED
Object Viborg 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: Viborg | Statement: [Midttrafik, operatesIn, Viborg]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Viborg
Context triple: [Midttrafik, operatesIn, Viborg]
  • A. Viborg chosen
    Viborg is one of Denmark’s oldest cities, historically significant as a medieval political and religious center on the Jutland peninsula.
  • B. Viborg
    Viborg is the Swedish name for the historic Karelian city of Vyborg, located near the Finnish border on the Gulf of Finland.
  • C. Vordingborg
    Vordingborg is a historic coastal town in southern Denmark known for the ruins of Vordingborg Castle and its prominent Goose Tower.
  • D. Fredericia
    Fredericia is a Danish coastal town in Jutland known for its historic 17th-century fortress and well-preserved ramparts.
  • E. Esbjerg
    Esbjerg is a major Danish port city on the North Sea, known for its offshore oil and wind industry, maritime heritage, and role as a regional economic center in western Jutland.
  • 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_69d8d38ae7e081908a98df1251842402 completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e5474d934481909b4afd5ef9031c73 completed April 19, 2026, 9:21 p.m.
Created at: April 10, 2026, 11:44 a.m.