Triple
T22619653
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | UM |
E558239
|
entity |
| Predicate | hasFaculty |
P141
|
FINISHED |
| Object | Faculty of Law |
—
|
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: Faculty of Law | Statement: [UM, hasFaculty, Faculty of Law]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Faculty of Law Context triple: [UM, hasFaculty, Faculty of Law]
-
A.
Faculty of Law
The Faculty of Law at the University of Freiburg is a prominent German law school known for its long academic tradition and comprehensive legal education and research programs.
-
B.
Faculty of Law
The Faculty of Law at the University of Milan is an academic division specializing in legal education and research, offering law degrees and related programs.
-
C.
Faculty of Law
The Faculty of Law at Keio University is a leading Japanese law school known for its rigorous legal education and influential contributions to the fields of law and political science.
-
D.
Faculty of Law
The Faculty of Law at the University of Djibouti is an academic division dedicated to legal education and research, training students in national and international law.
-
E.
Faculty of Law
The Faculty of Law at RDVV is an academic division specializing in legal education, research, and professional training in the field of law.
- 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_69e24545a8e08190bfa7482a2c725ff1 |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f16e383b048190a432c540185916d0 |
completed | April 29, 2026, 2:34 a.m. |
Created at: April 17, 2026, 3 p.m.