Triple

T19377414
Position Surface form Disambiguated ID Type / Status
Subject Russian invasion of Swedish Estonia E484706 entity
Predicate location P40 FINISHED
Object Swedish Estonia 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: Swedish Estonia | Statement: [Russian invasion of Swedish Estonia, location, Swedish Estonia]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Swedish Estonia
Context triple: [Russian invasion of Swedish Estonia, location, Swedish Estonia]
  • A. Swedish Estonia chosen
    Swedish Estonia was a dominion of the Swedish Empire on the eastern coast of the Baltic Sea, encompassing parts of present-day northern Estonia from the 16th to early 18th centuries.
  • B. Swedish Livonia
    Swedish Livonia was a former dominion of the Swedish Empire in the eastern Baltic region, encompassing parts of present-day Latvia and Estonia.
  • C. Szwedzka
    Szwedzka is a Warsaw Metro station serving the Targówek district in Poland.
  • D. Eston
    Eston is a town in North Yorkshire, England, historically associated with ironstone mining and now part of the borough of Redcar and Cleveland.
  • E. Öster
    Öster is a Swedish football club known formally as Östers IF, based in Växjö and historically successful in the Allsvenskan league.
  • 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_69d8e8d460d88190abf0591c5c9d2b0c completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e61a5cfbf48190ac60e3ffa6baa263 completed April 20, 2026, 12:21 p.m.
Created at: April 10, 2026, 1:35 p.m.