Triple
T26938209
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Slovenian statistical regions |
E678441
|
entity |
| Predicate | levelInNUTS |
P103898
|
FINISHED |
| Object | NUTS 3 |
—
|
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: NUTS 3 | Statement: [Slovenian statistical regions, levelInNUTS, NUTS 3]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: levelInNUTS Context triple: [Slovenian statistical regions, levelInNUTS, NUTS 3]
-
A.
levelInAdministrativeHierarchy
Indicates the relative position or rank of an administrative unit within a broader hierarchical administrative structure.
-
B.
sharesAdministrativeLevel
Indicates that two entities are associated with the same tier or rank within an administrative or governmental hierarchy.
-
C.
territorialLevel
chosen
Indicates the administrative or geographic tier at which something is defined, applied, or governed within a territorial hierarchy.
-
D.
jurisdictionLevel
Indicates the scope or tier of authority under which an entity or action is legally governed or regulated.
-
E.
highestAdministrativeLevelBelow
Indicates that one administrative unit is the most senior (top-ranked) level that is still subordinate to another specified administrative unit.
- 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_69eeeb4d69588190a7c912164a1c37b3 |
completed | April 27, 2026, 4:51 a.m. |
| NER | Named-entity recognition | batch_69f62050af2481909ce5687b36c4aabc |
completed | May 2, 2026, 4:03 p.m. |
| PD | Predicate disambiguation | batch_69f611af72ac819094598dd2530d7411 |
completed | May 2, 2026, 3:01 p.m. |
Created at: April 27, 2026, 6:17 a.m.