Triple
T7312295
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Taiwan Stock Exchange |
E168120
|
entity |
| Predicate | supportsMarginTrading |
P76247
|
FINISHED |
| Object | subject to regulation |
—
|
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: subject to regulation | Statement: [Taiwan Stock Exchange, supportsMarginTrading, subject to regulation]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportsMarginTrading Context triple: [Taiwan Stock Exchange, supportsMarginTrading, subject to regulation]
-
A.
marginTrading
Indicates engaging in trading activities using borrowed funds or leverage, typically by using existing assets as collateral.
-
B.
marginType
Indicates the type or category of margin applied in a given context, such as financial, layout, or safety margin.
-
C.
hasMarketMakers
Indicates that an entity is associated with one or more market makers who provide liquidity or facilitate trading for it.
-
D.
supportsBalanceProtection
Indicates that an entity provides or enables a balance protection feature that safeguards an account’s or position’s value against certain losses or negative changes.
-
E.
hasMarginOfSafety
Indicates that one entity possesses a sufficient buffer or safety allowance relative to another condition, threshold, or risk level to reduce the likelihood or impact of failure or loss.
- F. None of above. chosen
Provenance (4 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_69c6888d8e3c81909db79714903baf31 |
completed | March 27, 2026, 1:39 p.m. |
| NER | Named-entity recognition | batch_69c6ec00fef081909cb9768a70cabd80 |
completed | March 27, 2026, 8:43 p.m. |
| PD | Predicate disambiguation | batch_69c6e7705f4881909793071dee50c557 |
completed | March 27, 2026, 8:24 p.m. |
| PDg | Predicate description generation | batch_69c6eb88a2648190acc79eeee8733705 |
completed | March 27, 2026, 8:41 p.m. |
Created at: March 27, 2026, 3:02 p.m.