Triple
T12354181
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bulgarian currency board |
E294565
|
entity |
| Predicate | postRedenominationRate |
P11593
|
FINISHED |
| Object | 1 DEM = 1 BGN |
—
|
LITERAL 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: 1 DEM = 1 BGN | Statement: [Bulgarian currency board, postRedenominationRate, 1 DEM = 1 BGN]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: postRedenominationRate Context triple: [Bulgarian currency board, postRedenominationRate, 1 DEM = 1 BGN]
-
A.
redenomination
chosen
Indicates a change in the face value or unit of a currency, typically by replacing old denominations with new ones at a fixed conversion rate.
-
B.
denominationChange
Indicates a change in the monetary unit or face value associated with an entity, such as when currency or financial instruments are converted from one denomination to another.
-
C.
replacedCurrencyRate
Indicates that one currency exchange rate has been superseded or substituted by another rate in a given context.
-
D.
secondRedenominationYear
Indicates the year in which a second redenomination event (such as a currency or unit value reset) takes place.
-
E.
redenominationCount
Indicates the number of times a currency, asset, or unit has been redenominated or had its face value structurally adjusted.
- F. None of above.
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_69d6ab6ccbec8190b09e2d357aa80064 |
completed | April 8, 2026, 7:24 p.m. |
| NER | Named-entity recognition | batch_69d93f8bc60c8190b0ceb84093e70db4 |
completed | April 10, 2026, 6:20 p.m. |
| PD | Predicate disambiguation | batch_69d93ecb5efc819086a3530282278bb1 |
completed | April 10, 2026, 6:17 p.m. |
Created at: April 8, 2026, 9:54 p.m.