Triple
T5126246
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Saint John campus |
E115590
|
entity |
| Predicate | offersDegrees |
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: [Saint John campus, offersDegrees, bachelor’s degrees]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: offersDegrees Context triple: [Saint John campus, offersDegrees, bachelor’s degrees]
-
A.
offersDegree
chosen
Indicates that an institution or program provides a specific academic degree as an available qualification.
-
B.
offersFieldOfStudy
Indicates that an institution or program provides a particular field of study as an available area of academic focus.
-
C.
grantsDegreesFrom
Indicates that an institution has the authority to confer academic degrees originating from a specified source or program.
-
D.
offersLevelOfStudy
Indicates that an institution or program provides a particular level or type of study (e.g., undergraduate, graduate, doctoral) as an available option.
-
E.
offersEducationIn
Indicates that an entity provides or delivers educational programs, courses, or instruction in a specified field, subject, or area.
- 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_69bd444426bc819099ccd23f141e22aa |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd7d5a23908190a24e79d1b29d6fcf |
completed | March 20, 2026, 5:01 p.m. |
| PD | Predicate disambiguation | batch_69bd77aa68b88190a50dd736a72d2901 |
completed | March 20, 2026, 4:36 p.m. |
Created at: March 20, 2026, 1:42 p.m.