Triple
T454131
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | FHA 203(b) basic home mortgage program |
E7194
|
entity |
| Predicate | lenderType |
P13965
|
FINISHED |
| Object | FHA-approved lenders |
—
|
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: FHA-approved lenders | Statement: [FHA 203(b) basic home mortgage program, lenderType, FHA-approved lenders]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: lenderType Context triple: [FHA 203(b) basic home mortgage program, lenderType, FHA-approved lenders]
-
A.
loanType
Indicates the specific category or kind of loan associated with an entity or transaction.
-
B.
settlementType
Indicates the specific kind or category of human settlement an entity represents, such as a city, village, town, or hamlet.
-
C.
eligibleBorrower
Indicates that an entity meets the required conditions to be allowed to borrow (e.g., money, items, or resources) under a given set of rules or policies.
-
D.
typeOfContract
Indicates the specific kind or category of contractual agreement that applies between the related entities.
-
E.
ownershipType
Indicates the specific nature or category of the ownership relationship that one entity holds over another.
- 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_69a2e7e4676c81909ea0dbdecac0687c |
completed | Feb. 28, 2026, 1:04 p.m. |
| NER | Named-entity recognition | batch_69a2ef87cc7c8190a0fec933457821e2 |
completed | Feb. 28, 2026, 1:37 p.m. |
| PD | Predicate disambiguation | batch_69a2ede4de008190b5a6c159e741522e |
completed | Feb. 28, 2026, 1:30 p.m. |
| PDg | Predicate description generation | batch_69a2eeeb85f881909580a6a86332b4a5 |
completed | Feb. 28, 2026, 1:34 p.m. |
Created at: Feb. 28, 2026, 1:12 p.m.