Triple

T5441871
Position Surface form Disambiguated ID Type / Status
Subject Finnish railway network E122151 entity
Predicate connectsPort P845 FINISHED
Object Port of Turku E413226 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: Port of Turku | Statement: [Finnish railway network, connectsPort, Port of Turku]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Port of Turku
Context triple: [Finnish railway network, connectsPort, Port of Turku]
  • A. Port of Turku chosen
    The Port of Turku is a major Finnish seaport on the Baltic Sea that serves as an important hub for passenger ferries and cargo traffic between Finland and other Northern European countries.
  • B. Port of Helsinki
    The Port of Helsinki is Finland’s busiest seaport and a major passenger and cargo hub in the Baltic Sea region.
  • C. Port of Kemi
    The Port of Kemi is a Finnish seaport on the northern Gulf of Bothnia that serves as an important hub for regional industry and cargo traffic in Lapland.
  • D. Port of Tallinn
    The Port of Tallinn is Estonia’s largest and busiest seaport complex, serving as a major passenger and cargo hub on the Baltic Sea.
  • E. Port of Hanko
    The Port of Hanko is a key Finnish seaport on the southern coast that serves as an important hub for cargo and passenger traffic in the Baltic Sea region.
  • 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_69bd46400768819092925d461c0b8432 completed March 20, 2026, 1:06 p.m.
NER Named-entity recognition batch_69bd91c131648190b5a7f49efacc874a completed March 20, 2026, 6:28 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf70d2a5b481908a6fdc28bb2d2e11 completed March 22, 2026, 4:32 a.m.
Created at: March 20, 2026, 2:07 p.m.