Triple

T19523274
Position Surface form Disambiguated ID Type / Status
Subject Vidzeme region E488456 entity
Predicate borders P224 FINISHED
Object Kurzeme region 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: Kurzeme region | Statement: [Vidzeme region, borders, Kurzeme region]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kurzeme region
Context triple: [Vidzeme region, borders, Kurzeme region]
  • A. Vidzeme region
    Vidzeme region is a historical and cultural region in northeastern Latvia that includes the capital city Riga and is known for its forests, hills, and traditional Latvian heritage.
  • B. Kurzeme chosen
    Kurzeme is a historical and cultural region in western Latvia, known for its Baltic Sea coastline, forests, and traditional Latvian heritage.
  • C. Krajina region
    The Krajina region is a historically contested area in Croatia that was a Serb-majority enclave and key battleground during the Croatian War of Independence in the 1990s.
  • D. Dzūkija region
    Dzūkija region is a historical and ethnographic area in southeastern Lithuania known for its extensive forests, traditional villages, and rich cultural heritage.
  • E. Pomoravlje region
    The Pomoravlje region is a central Serbian area along the Morava River, known for its agricultural lands, industry, and key transport routes connecting northern and southern Serbia.
  • 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_69d8e8da8bec819081f400199491ccc3 completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e636392444819094f6a2aa1cdf3d42 completed April 20, 2026, 2:20 p.m.
Created at: April 10, 2026, 1:41 p.m.