Triple
T19032156
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | University of Western Macedonia |
E465766
|
entity |
| Predicate | hasDepartment |
P35
|
FINISHED |
| Object | Department of Informatics |
—
|
NE NERFINISHED |
How this triple was built (3 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: Department of Informatics | Statement: [University of Western Macedonia, hasDepartment, Department of Informatics]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Department of Informatics Context triple: [University of Western Macedonia, hasDepartment, Department of Informatics]
-
A.
Department of Informatics
The Department of Informatics at King’s College London is an academic unit focused on research and education in computer science, artificial intelligence, and related areas of information technology.
-
B.
Department of Informatics
The Department of Informatics is an academic unit within Indiana University’s Luddy School that focuses on the study and application of information technology in social, organizational, and human contexts.
-
C.
Department of Informatics
The Department of Informatics is an academic unit within UC Irvine’s Donald Bren School of Information and Computer Sciences that focuses on the study and design of sociotechnical, human-centered, and organizational aspects of computing and information systems.
-
D.
Department of Informatics
The Department of Informatics is an academic unit at the University of Belgrade specializing in computer science and information technology education and research.
-
E.
Department of Informatics
The Department of Informatics is an academic unit at the University of Minho’s School of Engineering focused on education and research in computer science and information technologies.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Department of Informatics Target entity description: The Department of Informatics is an academic unit at the University of Western Macedonia focused on education and research in computer science and information technology.
-
A.
Department of Informatics
The Department of Informatics is an academic unit of the Athens University of Economics and Business specializing in computer science and information systems education and research.
-
B.
Department of Informatics
The Department of Informatics is an academic unit at the University of Belgrade specializing in computer science and information technology education and research.
-
C.
Department of Informatics
The Department of Informatics is an academic unit at the University of Minho’s School of Engineering focused on education and research in computer science and information technologies.
-
D.
Department of Informatics
The Department of Informatics is an academic unit within UC Irvine’s Donald Bren School of Information and Computer Sciences that focuses on the study and design of sociotechnical, human-centered, and organizational aspects of computing and information systems.
-
E.
Department of Informatics
The Department of Informatics is an academic unit within Indiana University’s Luddy School that focuses on the study and application of information technology in social, organizational, and human contexts.
- F. None of above. 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_69d8dd0359648190bc2a9202c5cf29d2 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5d7410dd08190b08a7c0a2b8d67f3 |
completed | April 20, 2026, 7:35 a.m. |
Created at: April 10, 2026, 12:02 p.m.