Triple

T18246041
Position Surface form Disambiguated ID Type / Status
Subject Kurzeme E436956 entity
Predicate containsCity P294 FINISHED
Object Saldus 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: Saldus | Statement: [Kurzeme, containsCity, Saldus]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Saldus
Context triple: [Kurzeme, containsCity, Saldus]
  • A. Saldus chosen
    Saldus is a small town in western Latvia known for its regional cultural life and as a local economic and administrative center.
  • B. Kraainem
    Kraainem is a Dutch- and French-speaking suburban municipality on the eastern edge of Brussels in the Flemish Brabant province of Belgium.
  • C. Jelgava
    Jelgava is a city in central Latvia known for its historic Jelgava Palace and role as a regional cultural and educational center.
  • D. Paldiski
    Paldiski is a coastal town and former Soviet naval base in northwestern Estonia, located on the Pakri Peninsula by the Baltic Sea.
  • E. Cesvaine
    Cesvaine is a small historic town in eastern Latvia known for its picturesque Cesvaine Palace and surrounding natural landscapes.
  • 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_69d8b91104e08190a8241f7d260a5162 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4f7e6fbac8190bf252c4337f50c29 completed April 19, 2026, 3:42 p.m.
Created at: April 10, 2026, 10:33 a.m.