Triple
T37501432
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Western Michigan University |
E931971
|
entity |
| Predicate | hasGraduateCollege |
P11108
|
FINISHED |
| Object | The Graduate College |
—
|
NE NERFINISHED |
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: The Graduate College | Statement: [Western Michigan University, hasGraduateCollege, The Graduate College]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasGraduateCollege Context triple: [Western Michigan University, hasGraduateCollege, The Graduate College]
-
A.
hasGraduateInstitute
Indicates that an entity is associated with or offers a specific graduate-level educational institution or program.
-
B.
hasCollegeType
Indicates that a college or educational institution is classified as having a specific type or category (e.g., public, private, community, technical).
-
C.
hasGraduateDivision
chosen
Indicates that an institution or academic unit possesses an official graduate-level division or administrative body responsible for graduate programs.
-
D.
hasHighestDegree
Indicates that one entity possesses the highest academic degree attained by another entity.
-
E.
hasDoctoralDegree
Indicates that an entity holds a doctoral-level academic degree (such as a PhD, MD, or equivalent).
- 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_69f76ec5268481909ea01c73aeeefd42 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fbbc49da8c8190902bbb05d2477cab |
completed | May 6, 2026, 10:10 p.m. |
| PD | Predicate disambiguation | batch_69fbb13f34b08190bbbb220ac1e6e666 |
completed | May 6, 2026, 9:23 p.m. |
Created at: May 3, 2026, 4:17 p.m.