Triple
T8104678
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mamelodi Campus |
E189197
|
entity |
| Predicate | hasStudentSupportFocus |
P33631
|
FINISHED |
| Object | academic support |
—
|
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: academic support | Statement: [Mamelodi Campus, hasStudentSupportFocus, academic support]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasStudentSupportFocus Context triple: [Mamelodi Campus, hasStudentSupportFocus, academic support]
-
A.
hasStudentServices
chosen
Indicates that an entity provides or is associated with student support services for another entity or group.
-
B.
hasEducationalSupportFrom
Indicates that one entity receives educational assistance, guidance, or resources from another entity.
-
C.
hasStudentEnrollment
Indicates that a person or entity is enrolled as a student in a particular course, program, or educational institution.
-
D.
hasStudentMobility
Indicates that there is a relationship in which students move or participate across different institutions, locations, or programs (e.g., through exchanges, study abroad, or similar mobility activities).
-
E.
studentBodyFocus
Indicates that the primary attention, concern, or efforts are directed toward the student body as a whole.
- 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_69ca82b9d5848190a24672775d5c5011 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb42c0ce6481909887be82c8019383 |
completed | March 31, 2026, 3:42 a.m. |
| PD | Predicate disambiguation | batch_69cb04a2ed1c8190b73562321ad688bc |
completed | March 30, 2026, 11:17 p.m. |
Created at: March 30, 2026, 5:31 p.m.