Triple
T13204771
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | NDEA |
E314329
|
entity |
| Predicate | TitleIVFocus |
P66945
|
FINISHED |
| Object | student loans and fellowships |
—
|
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: student loans and fellowships | Statement: [NDEA, TitleIVFocus, student loans and fellowships]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: TitleIVFocus Context triple: [NDEA, TitleIVFocus, student loans and fellowships]
-
A.
fourthSingle
Indicates that an entity is the fourth individual item or occurrence in a sequence, considered on its own rather than as part of a group.
-
B.
fourthPartTitle
Indicates that the specified title is the fourth part in a sequence or multi-part work.
-
C.
statutoryFocus
chosen
Indicates that something is the primary subject, concern, or area of emphasis specified or governed by a statute or legal provision.
-
D.
fourthPartSubject
Indicates that the subject is the fourth part or component within a larger ordered whole or sequence.
-
E.
fourthWork
Indicates that one entity is the fourth work (in a series, sequence, or collection) associated with another entity.
- 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_69d806aee7308190b70a237ba2a6e3e1 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69d98c9b0cf08190a1d71cc94139539d |
completed | April 10, 2026, 11:49 p.m. |
| PD | Predicate disambiguation | batch_69d98bc938f081909f123bdf1263ff7f |
completed | April 10, 2026, 11:46 p.m. |
Created at: April 9, 2026, 9:17 p.m.