Triple

T18597543
Position Surface form Disambiguated ID Type / Status
Subject Midttrafik E454531 entity
Predicate operatesIn P82 FINISHED
Object Aarhus 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: Aarhus | Statement: [Midttrafik, operatesIn, Aarhus]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Aarhus
Context triple: [Midttrafik, operatesIn, Aarhus]
  • A. Aarhus chosen
    Aarhus is Denmark’s second-largest city, a major cultural and economic center on the Jutland peninsula known for its universities, vibrant arts scene, and historic harbor.
  • B. Aalborg
    Aalborg is a major city in northern Denmark known for its historic architecture, vibrant cultural life, and role as a regional economic and educational center.
  • C. Aarhus V
    Aarhus V is a district in the western part of Aarhus, Denmark, known for its residential areas and cultural diversity.
  • D. Odense
    Odense is a historic Danish city on the island of Funen, best known as the birthplace of fairy-tale author Hans Christian Andersen and a cultural hub with museums, festivals, and a vibrant literary heritage.
  • E. Randers
    Randers is a historic market town and one of the largest cities in eastern Jutland, Denmark, known for its old town center and location along the Gudenå River.
  • 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.