Triple
T37826697
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kansas community colleges |
E943078
|
entity |
| Predicate | offerCredentialType |
P80339
|
FINISHED |
| Object | certificates |
—
|
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: certificates | Statement: [Kansas community colleges, offerCredentialType, certificates]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: offerCredentialType Context triple: [Kansas community colleges, offerCredentialType, certificates]
-
A.
credentialOffered
chosen
Indicates that one party presents or makes available a credential to another party for potential acceptance or use.
-
B.
offeringType
Indicates the category or nature of what is being offered in a transaction or interaction (e.g., product, service, or other type of offering).
-
C.
offersQualificationType
Indicates that an entity provides or makes available a specific type or category of qualification.
-
D.
offersEnrollmentType
Indicates that an entity provides or makes available a specific type or category of enrollment option.
-
E.
welcomeOfferType
Indicates the type or category of a welcome offer provided in the context of an initial interaction or onboarding.
- 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_69f76eea4c8c8190a335aed5955cf2db |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69fea2d0a4d08190aa06aeb902a02d5a |
completed | May 9, 2026, 2:58 a.m. |
| PD | Predicate disambiguation | batch_69fea24698348190b9b992a8e7cdbcd0 |
completed | May 9, 2026, 2:56 a.m. |
Created at: May 3, 2026, 4:19 p.m.