Triple
T17078848
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Eliot House |
E414417
|
entity |
| Predicate | studentTypeServed |
P9355
|
FINISHED |
| Object | Harvard College undergraduates |
—
|
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: Harvard College undergraduates | Statement: [Eliot House, studentTypeServed, Harvard College undergraduates]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: studentTypeServed Context triple: [Eliot House, studentTypeServed, Harvard College undergraduates]
-
A.
admitsStudentsFrom
Indicates that an educational institution accepts or enrolls students who come from a specified source, such as a school, region, or program.
-
B.
schoolTypeOffered
Indicates the specific type or category of school that is provided or made available by an educational institution or organization.
-
C.
hasStudentServices
Indicates that an entity provides or is associated with student support services for another entity or group.
-
D.
servesStudentPopulation
chosen
Indicates that an entity provides services, resources, or support to a defined group of students.
-
E.
usesStudentsFor
Indicates that one entity employs or exploits students as a resource or means to carry out its activities or achieve its objectives.
- 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_69d886cef44c8190ba56c44b4e863e64 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3dbe0e9cc8190b6c4b6065b474d1d |
completed | April 18, 2026, 7:30 p.m. |
| PD | Predicate disambiguation | batch_69e35d642f74819098c014135e249b27 |
completed | April 18, 2026, 10:31 a.m. |
Created at: April 10, 2026, 5:34 a.m.