Triple

T20396326
Position Surface form Disambiguated ID Type / Status
Subject Amata E500212 entity
Predicate locatedIn P40 FINISHED
Object Vidzeme 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: Vidzeme region | Statement: [Amata, locatedIn, Vidzeme region]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Vidzeme region
Context triple: [Amata, locatedIn, Vidzeme region]
  • A. Vidzeme region chosen
    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. Dzūkija region
    Dzūkija region is a historical and ethnographic area in southeastern Lithuania known for its extensive forests, traditional villages, and rich cultural heritage.
  • C. Emilia region
    The Emilia region is a historical area in northern Italy, now part of Emilia-Romagna, known for its rich medieval art and architecture, including important Romanesque works.
  • D. Troizinia region
    The Troizinia region is a municipal area in northeastern Peloponnese, Greece, known for its coastal landscapes, agricultural villages, and historical ties to ancient Troezen.
  • E. Zalesye region
    The Zalesye region was a medieval northeastern area of Rus’ that became the core territory of the Vladimir-Suzdal principality and a cradle of the later Russian state.
  • 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.