Triple
T20597849
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Treviso Airport |
E506096
|
entity |
| Predicate | operator |
P179
|
FINISHED |
| Object | SAVE S.p.A. |
—
|
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: SAVE S.p.A. | Statement: [Treviso Airport, operator, SAVE S.p.A.]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: SAVE S.p.A. Context triple: [Treviso Airport, operator, SAVE S.p.A.]
-
A.
SAVE S.p.A.
chosen
SAVE S.p.A. is an Italian company that manages and operates Venice Marco Polo Airport and other related airport and infrastructure services.
-
B.
SACBO S.p.A.
SACBO S.p.A. is the company responsible for managing and operating Milan Bergamo Airport in northern Italy.
-
C.
Brenta Group
The Brenta Group is a prominent subrange of the Dolomites in northern Italy, known for its dramatic limestone peaks and popular alpine climbing routes.
-
D.
GESAP S.p.A.
GESAP S.p.A. is the company responsible for managing and operating Palermo’s main international airport in Sicily, Italy.
-
E.
Luso spa
Luso spa is a renowned Portuguese thermal resort known for its mineral-rich waters and wellness treatments, located in the municipality of Mealhada.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69e0b4ba6ae88190af871e1f9522c704 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6aa1d15b08190a720fc7cefbf333e |
completed | April 20, 2026, 10:35 p.m. |
Created at: April 16, 2026, 11:40 a.m.