Triple
T4630252
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Frosinone |
E101395
|
entity |
| Predicate | hasMotorwayAccess |
P385
|
FINISHED |
| Object | Autostrada A1 |
E494884
|
NE 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: Autostrada A1 | Statement: [Frosinone, hasMotorwayAccess, Autostrada A1]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Autostrada A1 Context triple: [Frosinone, hasMotorwayAccess, Autostrada A1]
-
A.
Autostrada A1
chosen
Autostrada A1 is Italy’s main north–south motorway, linking Milan to Naples and passing through several central regions including the area of Frosinone.
-
B.
Autostrada A10
Autostrada A10 is a major Italian motorway along the Ligurian coast that connects cities such as Genoa and Ventimiglia and continues toward the French border.
-
C.
Autostrada A5
Autostrada A5 is a major Italian motorway in northwestern Italy that connects Turin to the Aosta Valley and the Mont Blanc area near the French border.
-
D.
Autostrada A4
Autostrada A4 is a major Italian motorway running across northern Italy, connecting key cities such as Turin, Milan, Venice, and Trieste.
-
E.
A1 motorway
The A1 motorway is a major Swiss highway that runs across the country, connecting key cities such as Geneva, Lausanne, Bern, and Zurich.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69bd43d2f1c081908cd4b7ec48ecc73d |
completed | March 20, 2026, 12:55 p.m. |
| NER | Named-entity recognition | batch_69bd5a316ef48190831970ec914cf5a2 |
completed | March 20, 2026, 2:31 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c85695cc608190aa6ed016bd3f8929 |
completed | March 28, 2026, 10:30 p.m. |
Created at: March 20, 2026, 1:13 p.m.