Triple
T25981651
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Malawian pound |
E646085
|
entity |
| Predicate | exchangeRateOnReplacement |
P6186
|
FINISHED |
| Object | 2 Malawian kwacha = 1 Malawian pound |
—
|
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: 2 Malawian kwacha = 1 Malawian pound | Statement: [Malawian pound, exchangeRateOnReplacement, 2 Malawian kwacha = 1 Malawian pound]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: exchangeRateOnReplacement Context triple: [Malawian pound, exchangeRateOnReplacement, 2 Malawian kwacha = 1 Malawian pound]
-
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Indicates that one currency exchange rate has been superseded or substituted by another rate in a given context.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.
replacedCurrency
Indicates that one currency has been superseded and no longer used because another currency has taken its place.
-
D.
replacedCurrencyCode
Indicates that one currency has been superseded or replaced by another currency, identified by its code.
-
E.
exchangeRatio
Indicates the proportional rate at which one entity, resource, or value can be exchanged for another.
- 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_69e77e881fc08190ba1c8dc7e2a07f97 |
completed | April 21, 2026, 1:41 p.m. |
| NER | Named-entity recognition | batch_69f605102a1881909e83c4240c4ccdc6 |
completed | May 2, 2026, 2:07 p.m. |
| PD | Predicate disambiguation | batch_69f4a10480748190a2e67bd399fc435d |
completed | May 1, 2026, 12:48 p.m. |
Created at: April 22, 2026, 8:54 a.m.