Triple

T20396304
Position Surface form Disambiguated ID Type / Status
Subject Ligatne E500211 entity
Predicate languageUsed P238 FINISHED
Object Latvian 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: Latvian | Statement: [Ligatne, languageUsed, Latvian]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Latvian
Context triple: [Ligatne, languageUsed, Latvian]
  • A. Latvian chosen
    Latvian is a Baltic language spoken primarily in Latvia and one of the official languages of the European Union.
  • B. Latgalian
    Latgalian is an Eastern Baltic language variety closely related to Latvian, traditionally spoken by the Latgalian ethnic group in the Latgale region of eastern Latvia.
  • C. Latuvi
    Latuvi is a small rural village in the Sierra Norte region of Oaxaca, Mexico, known for its mountainous landscapes and traditional indigenous culture.
  • D. Latvians
    Latvians are a Baltic ethnic group native to Latvia, known for their distinct Latvian language, rich folk traditions, and cultural heritage along the eastern coast of the Baltic Sea.
  • E. Latn
    Latn is the ISO 15924 script code representing the Latin alphabet used for writing numerous modern languages worldwide.
  • 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_69e0b4a71ebc8190b153a36c738730f4 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6798b6640819085d5b12dc35633fe completed April 20, 2026, 7:07 p.m.
Created at: April 16, 2026, 11:28 a.m.