Triple

T8701565
Position Surface form Disambiguated ID Type / Status
Subject South Harbour, Helsinki E206543 entity
Predicate operator P179 FINISHED
Object Port of Helsinki E207486 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 Helsinki | Statement: [South Harbour, Helsinki, operator, Port of Helsinki]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Port of Helsinki
Context triple: [South Harbour, Helsinki, operator, Port of Helsinki]
  • A. Port of Helsinki chosen
    The Port of Helsinki is Finland’s busiest seaport and a major passenger and cargo hub in the Baltic Sea region.
  • B. Port of Turku
    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.
  • C. Port of Kotka
    The Port of Kotka is a major Finnish seaport on the Gulf of Finland that serves as an important hub for international cargo traffic and logistics.
  • D. Port of Pori
    The Port of Pori is a significant Finnish seaport on the west coast that serves as an important hub for the country’s maritime trade and cargo traffic.
  • E. Port of Mariehamn
    The Port of Mariehamn is the main maritime gateway of Åland’s capital, serving as a key passenger and cargo hub in the Baltic Sea.
  • 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_69ca83555b6c8190abe930dd397e863b completed March 30, 2026, 2:06 p.m.
NER Named-entity recognition batch_69cc58b38cf88190bfdcbac9c340cb96 completed March 31, 2026, 11:28 p.m.
NED1 Entity disambiguation (via context triple) batch_69cf28a0dd708190b12872883a2276c8 completed April 3, 2026, 2:40 a.m.
Created at: March 30, 2026, 6:34 p.m.