Triple

T14770865
Position Surface form Disambiguated ID Type / Status
Subject AMD E347127 entity
Predicate currencyName P7046 FINISHED
Object Armenian dram E69430 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: Armenian dram | Statement: [AMD, currencyName, Armenian dram]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Armenian dram
Context triple: [AMD, currencyName, Armenian dram]
  • A. Armenian dram chosen
    The Armenian dram is the official national currency of Armenia, used for everyday transactions and issued by the Central Bank of Armenia.
  • B. Azerbaijani manat
    The Azerbaijani manat is the official fiat currency of Azerbaijan, used for everyday transactions and issued by the Central Bank of Azerbaijan.
  • C. Georgian lari
    The Georgian lari is the official national currency of Georgia, introduced in 1995 to replace the kuponi and stabilize the country’s post-Soviet economy.
  • D. Transcaucasian ruble
    The Transcaucasian ruble was the short-lived monetary unit used by the Transcaucasian Democratic Federative Republic in the aftermath of the Russian Empire’s collapse.
  • E. Transnistrian ruble
    The Transnistrian ruble is the de facto currency used in the breakaway region of Transnistria, which is internationally recognized as part of Moldova.
  • 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_69d822e8896c819091169882f9b20486 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69dec81334e08190a77d760e507d00ed completed April 14, 2026, 11:04 p.m.
NED1 Entity disambiguation (via context triple) batch_69fe24b41df881908119e183b8299c48 completed May 8, 2026, 6 p.m.
Created at: April 10, 2026, 1:31 a.m.