Triple

T10108711
Position Surface form Disambiguated ID Type / Status
Subject Narva E218186 entity
Predicate countrySubdivision P766 FINISHED
Object Ida-Viru County E842085 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: Ida-Viru County | Statement: [Narva, countrySubdivision, Ida-Viru County]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ida-Viru County
Context triple: [Narva, countrySubdivision, Ida-Viru County]
  • A. Ida-Viru County chosen
    Ida-Viru County is an administrative region in northeastern Estonia known for its industrial centers, oil shale industry, and significant Russian-speaking population.
  • B. Viljandi County
    Viljandi County is a rural administrative region in southern Estonia known for its lakes, forests, and historic town of Viljandi.
  • C. Lääne-Viru County
    Lääne-Viru County is a northeastern administrative region of Estonia known for its coastal landscapes, historic manors, and the town of Rakvere.
  • D. Tartu County
    Tartu County is an administrative region in eastern Estonia centered around the university city of Tartu and known for its cultural, educational, and economic significance.
  • E. Võru County
    Võru County is a rural region in southeastern Estonia known for its distinct South Estonian (Võro) linguistic and cultural heritage.
  • 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_69ca83da93fc8190b54e44bc2b34857c completed March 30, 2026, 2:08 p.m.
NER Named-entity recognition batch_69cdd0cbd8a48190b2af6177d1249f58 completed April 2, 2026, 2:13 a.m.
NED1 Entity disambiguation (via context triple) batch_69d2e59ec83c8190a79fbb0d0de90310 completed April 5, 2026, 10:43 p.m.
Created at: March 30, 2026, 9:03 p.m.