Triple
T18972559
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | AUT |
E464205
|
entity |
| Predicate | campus |
P269
|
FINISHED |
| Object | North Campus |
—
|
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: North Campus | Statement: [AUT, campus, North Campus]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: North Campus Context triple: [AUT, campus, North Campus]
-
A.
North Campus
North Campus is one of the main campuses of Nelson Mandela University, housing a variety of academic, administrative, and student facilities.
-
B.
North Campus
North Campus is one of the main campuses of the University of Chile, housing a significant portion of its academic and research facilities.
-
C.
North Campus
North Campus is one of the main sites of TU Dortmund University, hosting a large portion of its academic buildings, research facilities, and student services.
-
D.
North Campus
North Campus is one of the main academic and facilities areas of Salem State University in Salem, Massachusetts.
-
E.
North Campus
North Campus is a major University of Michigan campus in Ann Arbor known for housing many of the university’s arts, engineering, and research facilities.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide. chosen
Provenance (2 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_69d8dd008af48190a97ff1c6488edf1b |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5d61cb3ac8190bfe29104166fa090 |
completed | April 20, 2026, 7:30 a.m. |
Created at: April 10, 2026, noon