Triple
T15688387
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Republican era |
E380259
|
entity |
| Predicate | currencyAtVariousTimes |
P83726
|
FINISHED |
| Object | silver yuan |
—
|
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: silver yuan | Statement: [Republican era, currencyAtVariousTimes, silver yuan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: currencyAtVariousTimes Context triple: [Republican era, currencyAtVariousTimes, silver yuan]
-
A.
currencyHistorically
chosen
Indicates that one entity has served as the official or commonly used currency of another entity during some period in the past.
-
B.
exchangeRateToPapiermark
Indicates the conversion rate or value of one currency in terms of the Papiermark.
-
C.
exchangeRateFixingDate
Indicates the specific date on which an exchange rate is determined or fixed for use in a financial transaction or agreement.
-
D.
exchangeRateContinuity
Indicates that the exchange rate between two currencies changes smoothly over time or conditions, without abrupt jumps or discontinuities.
-
E.
replacedCurrencyAtRate
Indicates that one currency was substituted for another at a specified exchange rate.
- 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_69d86d99e860819094b6957cde470f2c |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e04f4cee5481908699fbb2b7bdd2f6 |
completed | April 16, 2026, 2:54 a.m. |
| PD | Predicate disambiguation | batch_69deda8c856c8190882330114f9a1a5f |
completed | April 15, 2026, 12:23 a.m. |
Created at: April 10, 2026, 4:44 a.m.