Triple
T36626420
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | University Belt schools |
E904179
|
entity |
| Predicate | typicalProgramsOffered |
P170619
|
FINISHED |
| Object | undergraduate degree programs |
—
|
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: undergraduate degree programs | Statement: [University Belt schools, typicalProgramsOffered, undergraduate degree programs]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalProgramsOffered Context triple: [University Belt schools, typicalProgramsOffered, undergraduate degree programs]
-
A.
programOffered
Indicates that a particular program is made available or provided by a given entity (such as an institution, organization, or provider).
-
B.
offeredProgrammeType
chosen
Indicates the type or category of programme that is being offered by an entity.
-
C.
servesAcademicProgramsIn
Indicates that an institution or service provides academic support, resources, or offerings to the specified academic programs.
-
D.
academicProgramsMedium
Indicates the medium or format through which academic programs are delivered (e.g., online, in-person, hybrid).
-
E.
dayProgramOffered
Indicates that a particular day is one on which a specific program is available or scheduled to take place.
- 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_69f76e6ae750819096911e6e2d4d12c5 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_6a037c8e2c648190a65fc9c7872861af |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a037a0bf4b88190bdcfae9a14b51f0a |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:11 p.m.