Triple
T6824814
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | SIAC |
E156987
|
entity |
| Predicate | primaryMemberType |
P17104
|
FINISHED |
| Object | historically Black colleges and universities |
—
|
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: historically Black colleges and universities | Statement: [SIAC, primaryMemberType, historically Black colleges and universities]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primaryMemberType Context triple: [SIAC, primaryMemberType, historically Black colleges and universities]
-
A.
primaryUserType
Indicates the main or dominant category of user associated with an entity or interaction.
-
B.
primaryMembers
chosen
Indicates that the related entities are the main or most important members within a larger group or organization.
-
C.
primaryPatron
Indicates that one entity serves as the main or chief supporter, sponsor, or benefactor of another entity.
-
D.
primaryType
Indicates the main or most fundamental category or classification assigned to an entity, distinguishing it from any secondary or auxiliary types.
-
E.
primaryPatientType
Indicates the main category or classification of patient that is primarily associated with or targeted by an entity, action, or service.
- 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_69c6882a5b5c8190917a7db9ed36bad1 |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6d581ea5881908ba78c6bf1ce58ee |
completed | March 27, 2026, 7:07 p.m. |
| PD | Predicate disambiguation | batch_69c6d09bb4f881909bf20c188cb3e8e1 |
completed | March 27, 2026, 6:46 p.m. |
Created at: March 27, 2026, 2:18 p.m.