Triple
T23104254
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Subsidized Federal Stafford Loan |
E576117
|
entity |
| Predicate | disbursement |
P66766
|
FINISHED |
| Object | sent to school to pay tuition and fees first |
—
|
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: sent to school to pay tuition and fees first | Statement: [Subsidized Federal Stafford Loan, disbursement, sent to school to pay tuition and fees first]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: disbursement Context triple: [Subsidized Federal Stafford Loan, disbursement, sent to school to pay tuition and fees first]
-
A.
disburses
chosen
Indicates the act of paying out or distributing funds or resources from a source to a recipient.
-
B.
disbursementOption
Indicates the method or arrangement by which funds are paid out or distributed.
-
C.
dischargeContribution
Indicates that one party fulfills or settles an owed contribution, obligation, or share toward another party or collective.
-
D.
توزيع
Indicates the act of distributing or allocating something from one source to multiple recipients or locations.
-
E.
dischargesFrom
Indicates that something (such as a fluid, substance, or energy) flows or is released out of a specified source or origin.
- 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_69e245f4af548190898d434a64a1e774 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f18deb702c819099f2e2141706f00e |
completed | April 29, 2026, 4:49 a.m. |
| PD | Predicate disambiguation | batch_69ef89f020588190b43393e048e7eda3 |
completed | April 27, 2026, 4:08 p.m. |
Created at: April 17, 2026, 3:58 p.m.