Triple
T353778
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Swarthmore College |
E7499
|
entity |
| Predicate | financialAidPolicy |
P12170
|
FINISHED |
| Object | meets full demonstrated need |
—
|
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: meets full demonstrated need | Statement: [Swarthmore College, financialAidPolicy, meets full demonstrated need]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: financialAidPolicy Context triple: [Swarthmore College, financialAidPolicy, meets full demonstrated need]
-
A.
hasCommonFinancialAidPolicy
Indicates that two or more entities share the same rules, criteria, or framework governing financial aid policies.
-
B.
scholarshipType
Indicates the specific category or kind of scholarship associated with an entity.
-
C.
allowsNonScholarshipPrograms
Indicates that an entity permits the operation or participation of programs that do not offer scholarships.
-
D.
scholarshipEquivalency
Indicates that one scholarship is considered equal in value, coverage, or benefit to another scholarship or financial award.
-
E.
admissionPolicy
Indicates the rules or criteria governing whether and how entities are allowed to be admitted or granted access.
- F. None of above. chosen
Provenance (4 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_69a2e7e696948190bebc966535995e45 |
completed | Feb. 28, 2026, 1:04 p.m. |
| NER | Named-entity recognition | batch_69a2eb80f524819093f4c2c18c3d615f |
completed | Feb. 28, 2026, 1:20 p.m. |
| PD | Predicate disambiguation | batch_69a2e9571bd88190b6fcb16f21604720 |
completed | Feb. 28, 2026, 1:10 p.m. |
| PDg | Predicate description generation | batch_69a2ea0a4c448190a8a179daa9b90645 |
completed | Feb. 28, 2026, 1:13 p.m. |
Created at: Feb. 28, 2026, 1:08 p.m.