Triple

T14109686
Position Surface form Disambiguated ID Type / Status
Subject Østerport E339600 entity
Predicate connectsTo P845 FINISHED
Object Nørreport Station E1084770 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: Nørreport Station | Statement: [Østerport, connectsTo, Nørreport Station]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Nørreport Station
Context triple: [Østerport, connectsTo, Nørreport Station]
  • A. Nørreport station chosen
    Nørreport station is one of Copenhagen’s busiest central transport hubs, serving as a major interchange for metro, regional, and S-train services.
  • B. Frederiksberg Station
    Frederiksberg Station is a key Copenhagen Metro and S-train interchange located in the Frederiksberg district of Denmark’s capital.
  • C. Nørrebro station
    Nørrebro station is a major public transport hub in Copenhagen, Denmark, serving both S-train and metro lines in the Nørrebro district.
  • D. Ørestad station
    Ørestad station is a major transport hub in Copenhagen’s Ørestad district, combining a Copenhagen Metro stop with regional and local train services.
  • E. Hellerup Station
    Hellerup Station is a major railway and S-train hub in the northern part of Copenhagen, Denmark, serving as an important interchange for regional and commuter rail services.
  • 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_69d81c69b5c8819094aa1abf18302908 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de600caf308190ab6d8451ed4e3797 completed April 14, 2026, 3:41 p.m.
NED1 Entity disambiguation (via context triple) batch_69fef883f2b88190807d9157e8d45e3c completed May 9, 2026, 9:04 a.m.
Created at: April 9, 2026, 10:22 p.m.