Triple
T10550898
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shenzhen-Hong Kong Stock Connect |
E248942
|
entity |
| Predicate | settlementCurrencySouthbound |
P84841
|
FINISHED |
| Object | Hong Kong dollar |
—
|
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: Hong Kong dollar | Statement: [Shenzhen-Hong Kong Stock Connect, settlementCurrencySouthbound, Hong Kong dollar]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: settlementCurrencySouthbound Context triple: [Shenzhen-Hong Kong Stock Connect, settlementCurrencySouthbound, Hong Kong dollar]
-
A.
hasSettlementCurrency
chosen
Indicates that a financial transaction, contract, or account is settled using a specified currency.
-
B.
methodOfSettlement
Indicates the way in which a transaction, obligation, or dispute is resolved, completed, or paid.
-
C.
typeOfSettlement
Indicates the specific category or classification of a settlement (e.g., city, town, village) that characterizes what kind of settlement it is.
-
D.
settlementType
Indicates the specific kind or category of human settlement an entity represents, such as a city, village, town, or hamlet.
-
E.
settlementMode
Indicates the method or process by which a financial or transactional obligation is settled or completed between parties.
- 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_69d381c733c08190ab1dd6239f5f34ae |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d52710869c81909b6db1a190825bad |
completed | April 7, 2026, 3:47 p.m. |
| PD | Predicate disambiguation | batch_69d518fa0b4081909bffc936d78bd77b |
completed | April 7, 2026, 2:47 p.m. |
Created at: April 6, 2026, 12:34 p.m.