Triple
T18013646
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dupnitsa |
E430944
|
entity |
| Predicate | usesCurrency |
P188
|
FINISHED |
| Object | Bulgarian lev |
—
|
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: Bulgarian lev | Statement: [Dupnitsa, usesCurrency, Bulgarian lev]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bulgarian lev Context triple: [Dupnitsa, usesCurrency, Bulgarian lev]
-
A.
Bulgarian lev
chosen
The Bulgarian lev is the official national currency of Bulgaria, subdivided into 100 stotinki and pegged to the euro through a currency board arrangement.
-
B.
Macedonian denar
The Macedonian denar is the official fiat currency used in North Macedonia for everyday transactions and monetary policy.
-
C.
Moldovan leu
The Moldovan leu is the official monetary unit of Moldova, used for everyday transactions and financial operations within the country.
-
D.
Romanian leu
The Romanian leu is the official national currency of Romania, subdivided into 100 bani and issued by the National Bank of Romania.
-
E.
Serbian dinar
The Serbian dinar is the official national currency of Serbia, used for everyday transactions and monetary policy.
- 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_69d8b904530081908bf341d842464856 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4b521befc81908dff44f19aa3d580 |
completed | April 19, 2026, 10:57 a.m. |
Created at: April 10, 2026, 10:24 a.m.