Triple
T3924482
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Milchbuck |
E93240
|
entity |
| Predicate | serves |
P98
|
FINISHED |
| Object | Irchel campus |
E15534
|
NE 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: Irchel campus | Statement: [Milchbuck, serves, Irchel campus]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Irchel campus Context triple: [Milchbuck, serves, Irchel campus]
-
A.
Irchel campus
chosen
Irchel campus is a major University of Zurich site known for its science faculties, research facilities, and expansive park-like grounds in the city of Zurich.
-
B.
Schneiderberg campus
Schneiderberg campus is a main academic site of Leibniz University Hannover in Germany, housing several of its faculties and research facilities.
-
C.
Fürth campus
Fürth campus is a site of the University of Erlangen-Nuremberg located in the city of Fürth, Germany, hosting various academic and research facilities.
-
D.
Emek Campus
Emek Campus is one of the campuses of Gazi University in Turkey, hosting various academic and administrative facilities for the institution.
-
E.
White City campus
White City campus is a major Imperial College London site in west London focused on innovation, research, and collaboration with industry.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69aed96bfa1081908f7b30f2c647dee6 |
completed | March 9, 2026, 2:30 p.m. |
| NER | Named-entity recognition | batch_69aeed7dacdc8190854ebc13db2d24bc |
completed | March 9, 2026, 3:55 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b52873d5a881909c4c29f06b94a467 |
completed | March 14, 2026, 9:20 a.m. |
Created at: March 9, 2026, 3:23 p.m.