Triple
T13858024
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Desktop Underwriter |
E333113
|
entity |
| Predicate | supportsLoanType |
P24486
|
FINISHED |
| Object | conventional conforming mortgage |
—
|
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: conventional conforming mortgage | Statement: [Desktop Underwriter, supportsLoanType, conventional conforming mortgage]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportsLoanType Context triple: [Desktop Underwriter, supportsLoanType, conventional conforming mortgage]
-
A.
loanType
Indicates the specific category or kind of loan associated with an entity or transaction.
-
B.
lenderType
Indicates the classification or category of the lender involved in a lending relationship (e.g., bank, individual, institution).
-
C.
supportsProgramType
Indicates that one entity is capable of handling, offering, or being compatible with a specified type of program.
-
D.
supportsType
chosen
Indicates that one entity is capable of handling, accepting, or being compatible with a specified type.
-
E.
supportsAccountType
Indicates that one entity is compatible with, or able to operate for, a specified type or category of 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_69d81c5ba13c8190839315f54768acfd |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de02dc9f488190b7181dcb7e304632 |
completed | April 14, 2026, 9:03 a.m. |
| PD | Predicate disambiguation | batch_69dbc8691b608190a25a7c70a366b170 |
completed | April 12, 2026, 4:29 p.m. |
Created at: April 9, 2026, 10:14 p.m.