Triple

T5429040
Position Surface form Disambiguated ID Type / Status
Subject Port of Visby E121437 entity
Predicate isMainPortOf P2745 FINISHED
Object Visby E152807 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: Visby | Statement: [Port of Visby, isMainPortOf, Visby]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Visby
Context triple: [Port of Visby, isMainPortOf, Visby]
  • A. Visby chosen
    Visby is a well-preserved medieval Hanseatic town on the Swedish island of Gotland, renowned for its historic city wall and UNESCO World Heritage status.
  • B. Karlskrona
    Karlskrona is a historic Swedish coastal city and naval base known for its well-preserved maritime architecture and UNESCO-listed naval port.
  • C. Halmstad
    Halmstad is a coastal city in southwestern Sweden known for its historic town center, harbor, and role as a strategic site in Scandinavian conflicts.
  • D. Kalmar
    Kalmar is a historic coastal city in southeastern Sweden known for its medieval castle, role in the Kalmar Union, and connection to the island of Öland.
  • E. Malmö
    Malmö is a major coastal city in southern Sweden known for its historic center, modern architecture like the Turning Torso, and its role as a cultural and economic hub connected to Copenhagen via the Öresund Bridge.
  • 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_69bd463c65f0819082ee6483ab4b466a completed March 20, 2026, 1:06 p.m.
NER Named-entity recognition batch_69bd883d1bfc8190859bb05cfab065c8 completed March 20, 2026, 5:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf6c548a40819086910fbc39b21e90 completed March 22, 2026, 4:13 a.m.
Created at: March 20, 2026, 2:06 p.m.