Triple

T18245853
Position Surface form Disambiguated ID Type / Status
Subject Bank of Latvia E436950 entity
Predicate replacedCurrency P2867 FINISHED
Object Latvian rublis 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 rublis | Statement: [Bank of Latvia, replacedCurrency, Latvian rublis]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Latvian rublis
Context triple: [Bank of Latvia, replacedCurrency, Latvian rublis]
  • A. Latvian rublis chosen
    The Latvian rublis was the transitional currency used in Latvia in the early 1990s between the collapse of the Soviet ruble system and the introduction of the Latvian lats.
  • B. Latvian lats
    The Latvian lats was the national currency of Latvia until it was replaced by the euro in 2014.
  • C. Lithuanian grivna
    The Lithuanian grivna was a medieval silver ingot and unit of weight used as a basis for trade and taxation in the territories of the Grand Duchy of Lithuania.
  • D. Lithuanian litas
    The Lithuanian litas was the former national currency of Lithuania, used until the country adopted the euro in 2015.
  • E. Estonian kroon
    The Estonian kroon was the former national currency of Estonia, used from 1992 until the country adopted the euro in 2011.
  • 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_69d8b91104e08190a8241f7d260a5162 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4f7e6fbac8190bf252c4337f50c29 completed April 19, 2026, 3:42 p.m.
Created at: April 10, 2026, 10:33 a.m.