Triple
T454135
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | FHA 203(b) basic home mortgage program |
E7194
|
entity |
| Predicate | loanUse |
P2529
|
FINISHED |
| Object | purchase of a principal residence |
—
|
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: purchase of a principal residence | Statement: [FHA 203(b) basic home mortgage program, loanUse, purchase of a principal residence]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: loanUse Context triple: [FHA 203(b) basic home mortgage program, loanUse, purchase of a principal residence]
-
A.
loanType
Indicates the specific category or kind of loan associated with an entity or transaction.
-
B.
usedFor
Indicates that one entity serves a purpose, function, or role in accomplishing, enabling, or supporting another entity or activity.
-
C.
plannedUseOf
Indicates that one entity is intended or designated to be used for a specific purpose, function, or activity involving another entity.
-
D.
usageType
chosen
Indicates the specific manner, purpose, or context in which something is used or intended to be used.
-
E.
economicUse
Indicates that one entity utilizes another for economic purposes, such as production, trade, revenue generation, or cost-saving activities.
- 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_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. |
Created at: Feb. 28, 2026, 1:12 p.m.