Triple
T3045155
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Brighton campus |
E83427
|
entity |
| Predicate | distanceFromChestnutHillCampus |
P44786
|
FINISHED |
| Object | just west of main 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: just west of main campus | Statement: [Brighton campus, distanceFromChestnutHillCampus, just west of main campus]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: distanceFromChestnutHillCampus Context triple: [Brighton campus, distanceFromChestnutHillCampus, just west of main campus]
-
A.
distanceFromCampusCenter
Indicates the measured or specified distance between a given location and the central point of the campus.
-
B.
campusLocationRelativeToColumbia
Indicates the spatial relationship of a campus’s location relative to Columbia (e.g., where the campus is situated in relation to Columbia).
-
C.
distanceFromDowntown
Indicates the physical distance between a given location and the central downtown area.
-
D.
adjacentToCampusOf
Indicates that one entity is located next to or directly bordering the campus area of another entity.
-
E.
campusDistanceBetweenRivals
Indicates the physical distance separating the campuses of two rival institutions.
- 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_69ad8b24924c8190a9bb6f61d519e4ae |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69ad9b602ed881909a72662eb544866b |
completed | March 8, 2026, 3:53 p.m. |
| PD | Predicate disambiguation | batch_69ad961fc62c819087c4c3a44b00847d |
completed | March 8, 2026, 3:30 p.m. |
| PDg | Predicate description generation | batch_69ad97f6af3881909f4547967384114c |
completed | March 8, 2026, 3:38 p.m. |
Created at: March 8, 2026, 3:01 p.m.