Triple
T29628173
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | graduate programs of the University of Tokyo |
E755200
|
entity |
| Predicate | includesDegreeType |
P180358
|
FINISHED |
| Object | master’s degree |
—
|
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: master’s degree | Statement: [graduate programs of the University of Tokyo, includesDegreeType, master’s degree]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: includesDegreeType Context triple: [graduate programs of the University of Tokyo, includesDegreeType, master’s degree]
-
A.
eligibleDegree
Indicates that an academic degree qualifies its holder to be considered eligible for a particular program, position, or requirement.
-
B.
typeOfDegreeHandled
Indicates the specific academic degree type that an entity is responsible for managing or processing.
-
C.
grantsDegreeLevel
chosen
Indicates that an institution or program confers a specific academic degree level (such as bachelor’s, master’s, or doctorate) upon completion.
-
D.
includesHigherDegrees
Indicates that one entity’s set of academic degrees contains at least one degree that is at a higher level than those in another entity’s set.
-
E.
offersDegreeStructure
Indicates that an institution or program provides an organized curriculum leading to a specific academic degree.
- 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_69f0ef86b6ec8190a87fff07fd983b1e |
completed | April 28, 2026, 5:33 p.m. |
| NER | Named-entity recognition | batch_69ffdd05d1908190957deb11392f4595 |
completed | May 10, 2026, 1:19 a.m. |
| PD | Predicate disambiguation | batch_69ffdc0d33c881908b3483bee8a96540 |
completed | May 10, 2026, 1:14 a.m. |
Created at: April 28, 2026, 6:39 p.m.