Triple
T8150680
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | A-shares |
E190324
|
entity |
| Predicate | typicalInvestorBase |
P44408
|
FINISHED |
| Object | domestic investors in mainland China |
—
|
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: domestic investors in mainland China | Statement: [A-shares, typicalInvestorBase, domestic investors in mainland China]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalInvestorBase Context triple: [A-shares, typicalInvestorBase, domestic investors in mainland China]
-
A.
typeOfInvestor
Indicates the kind or category of investor that a given entity is classified as.
-
B.
investorObjective
Indicates that an entity’s goal, preference, or intended outcome in its role as an investor is directed toward another entity or investment.
-
C.
primaryInvestorBase
chosen
Indicates the main group or category of investors that predominantly provide capital or funding to an entity.
-
D.
investorAccess
Indicates that one party has permission or the ability to view, use, or interact with investment-related information, tools, or opportunities associated with another party or resource.
-
E.
typicalHoldingsType
Indicates the usual or most common category of holdings associated with an entity or account.
- 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_69ca82be7ba8819087de0147e9292c83 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb4481f19c8190aeec9bf029ad321b |
completed | March 31, 2026, 3:50 a.m. |
| PD | Predicate disambiguation | batch_69cb36a0847c8190af9038aef78319b3 |
completed | March 31, 2026, 2:51 a.m. |
Created at: March 30, 2026, 5:37 p.m.