Triple
T23230047
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kirkland College |
E581123
|
entity |
| Predicate | campusUseAfterMerger |
P16401
|
FINISHED |
| Object | Hamilton College campus |
—
|
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: Hamilton College campus | Statement: [Kirkland College, campusUseAfterMerger, Hamilton College campus]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: campusUseAfterMerger Context triple: [Kirkland College, campusUseAfterMerger, Hamilton College campus]
-
A.
campusLaterUsedFor
chosen
Indicates that a particular campus was subsequently repurposed or occupied for a different use at a later time.
-
B.
campusUse
Indicates that something is intended for, associated with, or occurring in the use or activities of a campus or campus community.
-
C.
campusUsedBy
Indicates that a particular campus is utilized or occupied by a specified group, organization, or set of entities.
-
D.
campusMovedTo
Indicates that the location of a campus has been relocated from one place to another.
-
E.
campus
Indicates that an entity is located on, associated with, or taking place within a particular campus.
- 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_69e246043c48819089bae72c9a9c306c |
completed | April 17, 2026, 2:39 p.m. |
| NER | Named-entity recognition | batch_69f1923131c081909c6e84b1a0c32e0d |
completed | April 29, 2026, 5:08 a.m. |
| PD | Predicate disambiguation | batch_69effcdadec0819092ec1749ee453b4e |
completed | April 28, 2026, 12:18 a.m. |
Created at: April 17, 2026, 4:09 p.m.