Triple
T242469
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Toppan family (Harvard benefactors) |
E4961
|
entity |
| Predicate | instanceOf |
P0
|
FINISHED |
| Object | Harvard University benefactor |
C3039
|
CONCEPT FINISHED |
How this triple was built (1 step)
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.
CD
Concept disambiguation
gpt-5-mini-2025-08-07
Target class: Harvard University benefactor Context triple: [Toppan family (Harvard benefactors), instanceOf, Harvard University benefactor]
-
A.
land-grant university
A land-grant university is a public institution of higher education designated by a government to receive the benefits of federal land grants, with a mission to provide accessible education and advance research and outreach in practical fields like agriculture, engineering, and the mechanical arts.
-
B.
private university
A private university is a higher education institution that is independently funded and operated, primarily through tuition, donations, and endowments rather than direct government support.
-
C.
Puritan minister
A Puritan minister is a religious leader in the Puritan tradition who preaches strict moral discipline, interprets scripture as the ultimate authority, and guides a community in living a pious, reformed Christian life.
-
D.
higher education organization
A higher education organization is an institution that provides post-secondary academic or professional education, conducts research, and grants recognized degrees or certifications.
-
E.
award-granting organization
An award-granting organization is an entity that establishes criteria, evaluates candidates, and formally recognizes individuals or groups with honors, prizes, or distinctions for their achievements or contributions.
- F. None of above. chosen
Provenance (1 batch)
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_69a257c3d0708190b0871c4269d273e6 |
completed | Feb. 28, 2026, 2:49 a.m. |
Created at: Feb. 28, 2026, 2:53 a.m.