Triple
T39097
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | European polytechnic institutes |
E774
|
entity |
| Predicate | collaborateWith |
P398
|
FINISHED |
| Object | industry partners |
—
|
LITERAL 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: industry partners | Statement: [European polytechnic institutes, collaborateWith, industry partners]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: collaborateWith Context triple: [European polytechnic institutes, collaborateWith, industry partners]
-
A.
coordinatedWith
Indicates that two or more entities have worked together in an organized, cooperative manner toward a shared task, goal, or activity.
-
B.
collaborationModel
Indicates the type or structure of cooperative interaction or joint work established between entities.
-
C.
worksWith
chosen
Indicates that two entities collaborate or perform tasks together in a shared work-related context.
-
D.
associatedWork
Indicates that there exists a related or connected work (such as a publication, creative piece, or project) that is meaningfully linked to the subject.
-
E.
hasCoauthor
Indicates that two or more entities have jointly authored the same work or publication.
- F. None of above.
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_69a247a8f6c08190bac804906d62ed5a |
completed | Feb. 28, 2026, 1:40 a.m. |
| NER | Named-entity recognition | batch_69a24b4d5bd08190a3a48eb26e67768c |
completed | Feb. 28, 2026, 1:56 a.m. |
| PD | Predicate disambiguation | batch_69a24ab6141881908701106aa97e4735 |
completed | Feb. 28, 2026, 1:53 a.m. |
Created at: Feb. 28, 2026, 1:46 a.m.