Triple
T457086
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Polish marka |
E7256
|
entity |
| Predicate | exchangeRateToSuccessor |
P6186
|
FINISHED |
| Object | 1 złoty = 1,800,000 marek |
—
|
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 złoty = 1,800,000 marek | Statement: [Polish marka, exchangeRateToSuccessor, 1 złoty = 1,800,000 marek]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: exchangeRateToSuccessor Context triple: [Polish marka, exchangeRateToSuccessor, 1 złoty = 1,800,000 marek]
-
A.
replacedCurrencyRate
Indicates that one currency exchange rate has been superseded or substituted by another rate in a given context.
-
B.
replacedCurrencyAtRate
chosen
Indicates that one currency was substituted for another at a specified exchange rate.
-
C.
exchangeRateRegulatedBy
Indicates that the determination or adjustment of an exchange rate is controlled, overseen, or constrained by a specified regulatory authority or mechanism.
-
D.
successorMonetarySystem
Indicates that one monetary system directly follows and replaces another in time or function.
-
E.
exchangeRateRegime
Indicates the type of system or policy a country or authority uses to manage and determine the value of its currency relative to other currencies.
- 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_69a2e7e5c5bc8190a1dc8178218fba40 |
completed | Feb. 28, 2026, 1:04 p.m. |
| NER | Named-entity recognition | batch_69a2efa1616481909399f92551a0c9e3 |
completed | Feb. 28, 2026, 1:37 p.m. |
| PD | Predicate disambiguation | batch_69a2ede614b88190be07425f5535f56d |
completed | Feb. 28, 2026, 1:30 p.m. |
Created at: Feb. 28, 2026, 1:12 p.m.