Triple
T16387404
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jefferson/USC station |
E397957
|
entity |
| Predicate | servesCampusGate |
P83608
|
FINISHED |
| Object | USC north side |
—
|
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: USC north side | Statement: [Jefferson/USC station, servesCampusGate, USC north side]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: servesCampusGate Context triple: [Jefferson/USC station, servesCampusGate, USC north side]
-
A.
cityCampusServes
Indicates that a city campus provides services, resources, or support to a particular population, area, or institution.
-
B.
servesUniversityCampus
chosen
Indicates that a service, facility, or entity provides support or functions specifically for a university campus.
-
C.
campusUse
Indicates that something is intended for, associated with, or occurring in the use or activities of a campus or campus community.
-
D.
governsCampus
Indicates that one entity has administrative or authoritative control over the operations and policies of a campus.
-
E.
isPartOfCampus
Indicates that one place, facility, or area is located within and belongs to a larger 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_69d87f2880b48190ae1a9673a3bbef80 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e3263e1534819081a6bf5006c611c5 |
completed | April 18, 2026, 6:35 a.m. |
| PD | Predicate disambiguation | batch_69e226f94dd48190b7b8e0e983738a67 |
completed | April 17, 2026, 12:26 p.m. |
Created at: April 10, 2026, 5:08 a.m.