Triple
T30150844
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bank of China |
E766389
|
entity |
| Predicate | currencyServices |
P85722
|
FINISHED |
| Object | renminbi |
—
|
NE NERFINISHED |
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: renminbi | Statement: [Bank of China, currencyServices, renminbi]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: currencyServices Context triple: [Bank of China, currencyServices, renminbi]
-
A.
currencyServiceType
Indicates the type or category of service associated with a particular currency.
-
B.
currencyProject
Indicates a relationship where a project is associated with, uses, or is denominated in a particular currency.
-
C.
exchangeCurrency
Indicates a relationship where one party converts or trades an amount of one currency for an equivalent amount of another currency.
-
D.
currencyOnboard
chosen
Indicates that a particular currency has been enabled, registered, or made available for use within a given system or context.
-
E.
currencyModel
Indicates that something uses, is based on, or conforms to a particular system or model of currency (e.g., monetary structure, denomination scheme, or valuation framework).
- 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_69f22479cd088190ab4c6f3fce39d1c5 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69fd783fed9c81909e792702636c4f1f |
completed | May 8, 2026, 5:44 a.m. |
| PD | Predicate disambiguation | batch_69fd7788e63c81909de22fdafcfe41c0 |
completed | May 8, 2026, 5:41 a.m. |
Created at: April 29, 2026, 7:20 p.m.