Triple
T23018638
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | TEACH Grant Program |
E573102
|
entity |
| Predicate | requiresAnnualCounseling |
P150698
|
FINISHED |
| Object | yes |
—
|
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: yes | Statement: [TEACH Grant Program, requiresAnnualCounseling, yes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: requiresAnnualCounseling Context triple: [TEACH Grant Program, requiresAnnualCounseling, yes]
-
A.
hasRecertificationRequirement
Indicates that an entity is subject to a requirement to periodically renew or update its certification to maintain its valid status.
-
B.
requiresAnnualFinancialReports
Indicates that one entity is obligated to provide annual financial reports to another entity or authority.
-
C.
requiresTrainingAt
Indicates that one entity must undergo or complete training at a specified organization, institution, or location as a prerequisite or requirement.
-
D.
annualPractice
Indicates that an action, event, or behavior occurs as a recurring practice on a yearly basis.
-
E.
requiresCertification
Indicates that one entity can only be performed, accessed, or considered valid if another entity has an appropriate certification.
- 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_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. |
| PDg | Predicate description generation | batch_69ef538b29c081908fa56ee35a1dcee7 |
completed | April 27, 2026, 12:16 p.m. |
Created at: April 17, 2026, 3:52 p.m.