Triple
T6001341
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | TD Direct Investing |
E133602
|
entity |
| Predicate | providesAccountType |
P38507
|
FINISHED |
| Object | cash account |
—
|
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: cash account | Statement: [TD Direct Investing, providesAccountType, cash account]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: providesAccountType Context triple: [TD Direct Investing, providesAccountType, cash account]
-
A.
accountType
chosen
Indicates the specific category or classification of an account within a system or context.
-
B.
supportsAccountType
Indicates that one entity is compatible with, or able to operate for, a specified type or category of account.
-
C.
hasBankType
Indicates that an entity is associated with or classified by a particular type or category of bank.
-
D.
billingAuthorityType
Indicates the specific role or category of authority responsible for issuing or managing a bill in the relationship between the parties.
-
E.
accessionType
Indicates the manner or category by which something is acquired, added, or admitted into a collection, system, or status.
- 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_69c00872444c8190bfaf1739dcec765c |
completed | March 22, 2026, 3:19 p.m. |
| NER | Named-entity recognition | batch_69c04ee7c0e08190a6e78969448b070a |
completed | March 22, 2026, 8:19 p.m. |
| PD | Predicate disambiguation | batch_69c049e3316c819087ea635fa7ee8472 |
completed | March 22, 2026, 7:58 p.m. |
Created at: March 22, 2026, 4:05 p.m.