Triple

T20185917
Position Surface form Disambiguated ID Type / Status
Subject Vääna Manor E492859 entity
Predicate locatedIn P40 FINISHED
Object Vääna 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: Vääna | Statement: [Vääna Manor, locatedIn, Vääna]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Vääna
Context triple: [Vääna Manor, locatedIn, Vääna]
  • A. Vääna chosen
    Vääna is a village in northern Estonia known for its historic manor and coastal location near the capital, Tallinn.
  • B. Veele
    Veele is a small village in the municipality of Vlagtwedde in the province of Groningen in the Netherlands.
  • C. Vääna-Jõesuu
    Vääna-Jõesuu is a coastal village in northern Estonia known for its sandy beach and location at the mouth of the Vääna River.
  • D. Vesanto
    Vesanto is a small rural municipality in eastern Finland known for its lakes, forests, and traditional Finnish countryside.
  • E. Valga
    Valga is a small border town in southern Estonia known for forming a twin city with Valka in Latvia.
  • 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_69da6268a034819081cbd9ea5a1c9475 completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e668f2c03c819096336462f59dba91 completed April 20, 2026, 5:57 p.m.
Created at: April 11, 2026, 11:36 p.m.