Triple

T20463660
Position Surface form Disambiguated ID Type / Status
Subject Laagri E501992 entity
Predicate locatedIn P40 FINISHED
Object Saue Parish 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: Saue Parish | Statement: [Laagri, locatedIn, Saue Parish]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Saue Parish
Context triple: [Laagri, locatedIn, Saue Parish]
  • A. Saue Parish chosen
    Saue Parish is a rural municipality in northern Estonia known for its small towns, villages, and proximity to the capital region around Tallinn.
  • B. Luunja Parish
    Luunja Parish is a rural municipality in eastern Estonia known for its agricultural landscape and proximity to the city of Tartu.
  • C. Nõo Parish
    Nõo Parish is a rural municipality in southeastern Estonia known for its small communities, forests, and proximity to the city of Tartu.
  • D. Kiili Parish
    Kiili Parish is a rural municipality in northern Estonia known for its small communities and proximity to the capital, Tallinn, within Harju County.
  • E. Haljala Parish
    Haljala Parish is a rural municipality in northern Estonia known historically as the birthplace of notable figures such as writer Friedrich Reinhold Kreutzwald.
  • 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_69e0b4ad4940819098cf2ff6413574e5 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e696a88374819087e7b97c83074d2c completed April 20, 2026, 9:12 p.m.
Created at: April 16, 2026, 11:33 a.m.