Triple
T23018624
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | TEACH Grant Program |
E573102
|
entity |
| Predicate | obligationDocument |
P6254
|
FINISHED |
| Object | TEACH Grant Agreement to Serve or Repay |
—
|
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: TEACH Grant Agreement to Serve or Repay | Statement: [TEACH Grant Program, obligationDocument, TEACH Grant Agreement to Serve or Repay]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: obligationDocument Context triple: [TEACH Grant Program, obligationDocument, TEACH Grant Agreement to Serve or Repay]
-
A.
obligationType
Indicates the specific kind or category of duty, requirement, or commitment that applies within an obligation relationship.
-
B.
filingObligation
Indicates that an entity is required to submit specified documents or reports to an authority within defined conditions or timeframes.
-
C.
obligation
chosen
Indicates that one entity is bound or required to perform a duty, action, or fulfill a condition toward another entity or according to a rule or agreement.
-
D.
issuedDocument
Indicates that one entity has formally created and provided an official document to another entity.
-
E.
issuedDocumentOn
Indicates that an entity formally produced or released a document on a specific date or occasion.
- 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_69e245b764cc8190a51be76f1d9611e1 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f183e777cc81908c0b0bfd9d5a717c |
completed | April 29, 2026, 4:07 a.m. |
| PD | Predicate disambiguation | batch_69ef3b9cd5488190bcd23183179f48cd |
completed | April 27, 2026, 10:34 a.m. |
Created at: April 17, 2026, 3:52 p.m.