Triple
T21084205
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Iranian universities |
E519444
|
entity |
| Predicate | offerDegree |
P49
|
FINISHED |
| Object | bachelor’s degrees |
—
|
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: bachelor’s degrees | Statement: [Iranian universities, offerDegree, bachelor’s degrees]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: offerDegree Context triple: [Iranian universities, offerDegree, bachelor’s degrees]
-
A.
offersDegree
chosen
Indicates that an institution or program provides a specific academic degree as an available qualification.
-
B.
eligibleDegree
Indicates that an academic degree qualifies its holder to be considered eligible for a particular program, position, or requirement.
-
C.
offersLevelOfStudy
Indicates that an institution or program provides a particular level or type of study (e.g., undergraduate, graduate, doctoral) as an available option.
-
D.
offersGrades
Indicates that one entity provides or assigns academic grades to another entity.
-
E.
offersFieldEducation
Indicates that one entity provides practical, field-based educational or training opportunities to another.
- 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_69e0b507dd9081908fb8bfcbef4c8b46 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e70948704481908b8b75a2ecc42bb6 |
completed | April 21, 2026, 5:21 a.m. |
| PD | Predicate disambiguation | batch_69e5dbfcd5e881908f1e4e0d2d237856 |
completed | April 20, 2026, 7:55 a.m. |
Created at: April 16, 2026, 2:49 p.m.