Triple
T4439189
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Undergraduate Admissions Office of UC Berkeley |
E95726
|
entity |
| Predicate | typeOfAdmissions |
P24289
|
FINISHED |
| Object | freshman admissions |
—
|
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: freshman admissions | Statement: [Undergraduate Admissions Office of UC Berkeley, typeOfAdmissions, freshman admissions]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfAdmissions Context triple: [Undergraduate Admissions Office of UC Berkeley, typeOfAdmissions, freshman admissions]
-
A.
admissionType
chosen
Indicates the category or manner in which an entity (such as a person or case) is formally accepted or admitted into a system, institution, or process.
-
B.
admissionsSystem
Indicates a relationship where an entity functions as or is associated with a system that manages or processes admissions decisions or applications.
-
C.
admissionsLevel
Indicates the degree or category of access, entry, or acceptance granted in an admissions context.
-
D.
admissionsBasedOn
Indicates that acceptance or entry decisions are determined according to specified criteria, factors, or conditions.
-
E.
controlsAdmissionsFor
Indicates that one entity has authority or responsibility over managing and deciding admissions for another entity.
- 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_69b3453ea2b48190a26f154b3b8fece5 |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b355aaa9288190b95d875d343d6ee5 |
completed | March 13, 2026, 12:09 a.m. |
| PD | Predicate disambiguation | batch_69b34f6078cc8190831b89f404198cc5 |
completed | March 12, 2026, 11:42 p.m. |
Created at: March 12, 2026, 11:31 p.m.