Triple

T20486641
Position Surface form Disambiguated ID Type / Status
Subject Pirita Beach E502611 entity
Predicate nearby P350 FINISHED
Object Pirita Marina 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: Pirita Marina | Statement: [Pirita Beach, nearby, Pirita Marina]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Pirita Marina
Context triple: [Pirita Beach, nearby, Pirita Marina]
  • A. Vuosaari Harbour
    Vuosaari Harbour is a major cargo and logistics port area in eastern Helsinki, Finland, serving as the city’s primary freight hub.
  • B. Paljassaare Harbour chosen
    Paljassaare Harbour is a smaller cargo and industrial port area in Tallinn, Estonia, primarily handling bulk and mixed goods within the Port of Tallinn complex.
  • C. Port of Hamina
    The Port of Hamina is a key Finnish seaport on the Gulf of Finland that serves as an important hub for international cargo traffic, particularly trade with Russia and other Eastern European markets.
  • D. Port of Kymi
    Port of Kymi is a coastal harbor facility in the town of Kymi in Greece, serving local maritime transport and regional shipping activities.
  • E. Lutakko harbour
    Lutakko harbour is a lakeside port area in Jyväskylä, Finland, known for its marina, events, and recreational waterfront.
  • 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_69e0b4af32848190aea80682b44d5d6e completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e69b5b96c0819080c47064143cdbc9 completed April 20, 2026, 9:32 p.m.
Created at: April 16, 2026, 11:34 a.m.