Triple
T1201672
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Federal Pell Grant Program |
E25794
|
entity |
| Predicate | maximumAwardChanges |
P25523
|
FINISHED |
| Object | annually by federal law and appropriations |
—
|
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: annually by federal law and appropriations | Statement: [Federal Pell Grant Program, maximumAwardChanges, annually by federal law and appropriations]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: maximumAwardChanges Context triple: [Federal Pell Grant Program, maximumAwardChanges, annually by federal law and appropriations]
-
A.
lastAwarded
Indicates the most recent time or instance at which an entity received a particular award.
-
B.
awardedFrequency
Indicates how often an award or recognition is given within a specified time period.
-
C.
canAward
Indicates that one entity has the authority or ability to grant an award, honor, or recognition to another entity.
-
D.
positionAwarded
Indicates that a specific position, role, or title has been formally granted to an entity (such as a person or organization).
-
E.
hasAwarded
Indicates that one entity has given or conferred an award to another entity.
- 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_69a49429f5ec8190a6a205eb0ae81e5e |
completed | March 1, 2026, 7:31 p.m. |
| NER | Named-entity recognition | batch_69a4bd9fece4819089a6a2d61e61fa2e |
completed | March 1, 2026, 10:28 p.m. |
| PD | Predicate disambiguation | batch_69a4bb5ed2b88190aab992913957e1cf |
completed | March 1, 2026, 10:19 p.m. |
| PDg | Predicate description generation | batch_69a4bcc82e38819081c3615e1cc7a66f |
completed | March 1, 2026, 10:25 p.m. |
Created at: March 1, 2026, 7:46 p.m.