Triple
T30568192
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | University of Žilina |
E778044
|
entity |
| Predicate | ERASMUSCode |
P11615
|
FINISHED |
| Object | SK ZILINA01 |
—
|
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: SK ZILINA01 | Statement: [University of Žilina, ERASMUSCode, SK ZILINA01]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ERASMUSCode Context triple: [University of Žilina, ERASMUSCode, SK ZILINA01]
-
A.
ErasmusCode
chosen
Indicates a relationship where an entity is associated with, identified by, or governed through an Erasmus-specific code or identifier.
-
B.
campusCode
Indicates the specific campus identifier associated with an entity, typically distinguishing which campus a person, program, or resource belongs to.
-
C.
offersStudyAbroad
Indicates that an institution or program provides opportunities for participants to study in a foreign country.
-
D.
educationAbroadPurpose
Indicates that an instance of education abroad is associated with a specific purpose or intended goal for undertaking that study outside one’s home country.
-
E.
university2
Indicates a relationship where an entity is a university associated with, attended by, or otherwise linked to another entity.
- 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_69f2249f8c148190ae7eb3912cde112a |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f689108d448190ba08a76cfaea85ce |
completed | May 2, 2026, 11:30 p.m. |
| PD | Predicate disambiguation | batch_69f67e42d6688190b60e91d2c388c555 |
completed | May 2, 2026, 10:44 p.m. |
Created at: April 29, 2026, 8:21 p.m.