Triple
T339222
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Belarusian ruble |
E6795
|
entity |
| Predicate | redenominationDate |
P11594
|
FINISHED |
| Object | 1 July 2016 |
—
|
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 July 2016 | Statement: [Belarusian ruble, redenominationDate, 1 July 2016]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: redenominationDate Context triple: [Belarusian ruble, redenominationDate, 1 July 2016]
-
A.
redenominationCount
Indicates the number of times a currency, asset, or unit has been redenominated or had its face value structurally adjusted.
-
B.
firstRedenominationYear
Indicates the year in which a currency or financial unit was first redenominated (i.e., its face value was officially recalibrated or replaced).
-
C.
thirdRedenominationYear
Indicates the calendar year in which the third redenomination event of a currency or financial instrument took place.
-
D.
secondRedenominationYear
Indicates the year in which a second redenomination event (such as a currency or unit value reset) takes place.
-
E.
legalTenderUntil
Indicates that a form of money is officially recognized as valid payment only up to a specified date or time.
- F. None of above. chosen
Provenance (4 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_69a2e79434908190a9d5afe415153ad9 |
completed | Feb. 28, 2026, 1:03 p.m. |
| NER | Named-entity recognition | batch_69a2eae3a27c81909fc7deb600125fb1 |
completed | Feb. 28, 2026, 1:17 p.m. |
| PD | Predicate disambiguation | batch_69a2e95067e88190a914a1c1d0283dfc |
completed | Feb. 28, 2026, 1:10 p.m. |
| PDg | Predicate description generation | batch_69a2ea09a5e881908b313cb37409a4f9 |
completed | Feb. 28, 2026, 1:13 p.m. |
Created at: Feb. 28, 2026, 1:08 p.m.