Triple
T28926986
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Farm Lane Bridge |
E733677
|
entity |
| Predicate | isInCampus |
P36352
|
FINISHED |
| Object | Michigan State University |
—
|
NE NERFINISHED |
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: Michigan State University | Statement: [Farm Lane Bridge, isInCampus, Michigan State University]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isInCampus Context triple: [Farm Lane Bridge, isInCampus, Michigan State University]
-
A.
isPartOfCampus
chosen
Indicates that one place, facility, or area is located within and belongs to a larger campus.
-
B.
operatesOnCampus
Indicates that an organization or entity conducts its activities or business within the grounds or facilities of a particular campus.
-
C.
isCampusFor
Indicates that a location serves as the campus associated with a particular institution or organization.
-
D.
isCentralizedCampus
Indicates that a campus is organized with its main facilities and activities concentrated in a single, central location rather than being dispersed across multiple sites.
-
E.
hasSurfaceCampus
Indicates that one entity (typically an institution) maintains a physical campus or site located on the surface of another entity (such as a planet or celestial body).
- 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_69f05b0b49b08190b8994b339c7980f6 |
completed | April 28, 2026, 7 a.m. |
| NER | Named-entity recognition | batch_69f65b4fee008190bc43ed7e719872db |
completed | May 2, 2026, 8:15 p.m. |
| PD | Predicate disambiguation | batch_69f659d02f1c8190831758ac52bb54e4 |
completed | May 2, 2026, 8:08 p.m. |
Created at: April 28, 2026, 8:24 a.m.