Triple

T19581320
Position Surface form Disambiguated ID Type / Status
Subject Vanasadam E489991 entity
Predicate operator P179 FINISHED
Object Port of Tallinn company 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: Port of Tallinn company | Statement: [Vanasadam, operator, Port of Tallinn company]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Port of Tallinn company
Context triple: [Vanasadam, operator, Port of Tallinn company]
  • A. Port of Hanko Ltd
    Port of Hanko Ltd is the company responsible for managing and operating Finland’s southernmost commercial seaport at Hanko.
  • B. Tallinna Sadam AS chosen
    Tallinna Sadam AS is an Estonian state-owned port and logistics company that manages and develops the Port of Tallinn and related maritime infrastructure.
  • C. Hartwall
    Hartwall is a Finnish beverage company best known for producing soft drinks, beers, and bottled waters.
  • D. Murmansk Shipping Company
    Murmansk Shipping Company is a Russian maritime transport enterprise historically known for operating nuclear-powered icebreakers and supporting Arctic shipping routes.
  • E. 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.
  • 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_69d8e8dd9374819098e36349b3211663 completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e640281b7c8190be44268a58df058f completed April 20, 2026, 3:03 p.m.
Created at: April 10, 2026, 1:42 p.m.