Triple

T6746616
Position Surface form Disambiguated ID Type / Status
Subject Latgale E154233 entity
Predicate majorCity P316 FINISHED
Object Krāslava E615706 NE FINISHED

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: Krāslava | Statement: [Latgale, majorCity, Krāslava]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Krāslava
Context triple: [Latgale, majorCity, Krāslava]
  • A. Lvov
    Lvov is a Russian noble family name most notably borne by Georgy Lvov, the first head of the Russian Provisional Government after the February Revolution of 1917.
  • B. Kovno
    Kovno is the historical name for Kaunas, a major city in Lithuania that was once part of the Russian Empire and had a significant Jewish community.
  • C. Vilna
    Vilna is the historical name for Vilnius, the capital city of Lithuania and a major cultural and political center of the region.
  • D. Krāslava Municipality chosen
    Krāslava Municipality is a local government area in eastern Latvia centered around the town of Krāslava, near the border with Belarus.
  • E. Mitau
    Mitau, historically known as the capital of the Duchy of Courland and Semigallia, is the former German name for the city now called Jelgava in present-day Latvia.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69c6880ef37881909268a5a7299b9293 completed March 27, 2026, 1:37 p.m.
NER Named-entity recognition batch_69c6d1b8a0f0819086b802983e8ffcb6 completed March 27, 2026, 6:51 p.m.
NED1 Entity disambiguation (via context triple) batch_69c71a76f0c8819097e19e016988f0b4 completed March 28, 2026, 12:01 a.m.
Created at: March 27, 2026, 2:10 p.m.