Triple
T22619671
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | UM |
E558239
|
entity |
| Predicate | hasLibrary |
P35
|
FINISHED |
| Object | Maastricht University Library |
—
|
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: Maastricht University Library | Statement: [UM, hasLibrary, Maastricht University Library]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Maastricht University Library Context triple: [UM, hasLibrary, Maastricht University Library]
-
A.
Leiden University Libraries
Leiden University Libraries is the academic library system of Leiden University in the Netherlands, renowned for its extensive historical and research collections.
-
B.
Ghent University Library
Ghent University Library is the central academic library system of Ghent University in Belgium, renowned for its extensive research collections and iconic modernist Book Tower.
-
C.
University Library of Erasmus University Rotterdam
The University Library of Erasmus University Rotterdam is the central academic library of Erasmus University, providing extensive study spaces, collections, and research support to students and staff in Rotterdam.
-
D.
University of Groningen Library
The University of Groningen Library is the academic library system of the University of Groningen, providing extensive research resources, study facilities, and digital services to students and scholars.
-
E.
University Library Radboud University
University Library Radboud University is the central academic library system of Radboud University in Nijmegen, providing scholarly resources, study spaces, and research support to students and staff.
- 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: Maastricht University Library Target entity description: Maastricht University Library is the academic library system of Maastricht University in the Netherlands, providing study spaces, collections, and digital resources to support the university’s education and research.
-
A.
Leiden University Libraries
Leiden University Libraries is the academic library system of Leiden University in the Netherlands, renowned for its extensive historical and research collections.
-
B.
Ghent University Library
Ghent University Library is the central academic library system of Ghent University in Belgium, renowned for its extensive research collections and iconic modernist Book Tower.
-
C.
University Library of Erasmus University Rotterdam
The University Library of Erasmus University Rotterdam is the central academic library of Erasmus University, providing extensive study spaces, collections, and research support to students and staff in Rotterdam.
-
D.
University of Groningen Library
The University of Groningen Library is the academic library system of the University of Groningen, providing extensive research resources, study facilities, and digital services to students and scholars.
-
E.
University Library Radboud University
University Library Radboud University is the central academic library system of Radboud University in Nijmegen, providing scholarly resources, study spaces, and research support to students and staff.
- 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_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.