Triple
T4894104
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | U.S. savings banks |
E109631
|
entity |
| Predicate | typicalAssetClass |
P28970
|
FINISHED |
| Object | residential mortgages |
—
|
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: residential mortgages | Statement: [U.S. savings banks, typicalAssetClass, residential mortgages]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalAssetClass Context triple: [U.S. savings banks, typicalAssetClass, residential mortgages]
-
A.
notableAssetClass
Indicates that an entity is significantly associated with, or recognized for, a particular class of assets.
-
B.
coversAssetClass
Indicates that one entity (such as a product, service, or policy) includes, applies to, or provides coverage for a specified asset class.
-
C.
typicalHoldingsType
chosen
Indicates the usual or most common category of holdings associated with an entity or account.
-
D.
assetType
Indicates the specific category or classification of an asset within a broader asset framework or system.
-
E.
investmentType
Indicates the specific category or nature of an investment associated with an entity or transaction.
- 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_69bd4410bbf88190aad50d2451c863d6 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd6ffabccc81909115ece1b04e2061 |
completed | March 20, 2026, 4:04 p.m. |
| PD | Predicate disambiguation | batch_69bd6c2e7b5c8190b8bf9d616dfa24f0 |
completed | March 20, 2026, 3:47 p.m. |
Created at: March 20, 2026, 1:28 p.m.