Triple
T20490108
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Il Lombardia |
E502717
|
entity |
| Predicate | hasClimb |
P128091
|
FINISHED |
| Object | Muro di Sormano |
—
|
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: Muro di Sormano | Statement: [Il Lombardia, hasClimb, Muro di Sormano]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Muro di Sormano Context triple: [Il Lombardia, hasClimb, Muro di Sormano]
-
A.
Muro di Sormano
chosen
Muro di Sormano is a famously steep and iconic cycling climb in Italy’s Lombardy region, renowned for its extreme gradients and frequent inclusion in professional road races.
-
B.
Rocca del Sasso
Rocca del Sasso is a historic fortress overlooking the town of Verucchio in Italy, known for its medieval architecture and panoramic views of the surrounding landscape.
-
C.
Colle di Tora
Colle di Tora is a small Italian town in the Lazio region, known for its scenic position on the shores of Lake Turano.
-
D.
Rocca di Sala
Rocca di Sala is a historic hilltop fortress overlooking the town of Pietrasanta in Tuscany, Italy.
-
E.
Rocca di Mezzo
Rocca di Mezzo is a mountain town in Italy’s Abruzzo region, known for its alpine landscapes, ski tourism, and traditional stone architecture.
- 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_69e0b4b0373881909dd3e9387f82eab4 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e69cb8e7848190a1dc497a10ae798c |
completed | April 20, 2026, 9:38 p.m. |
Created at: April 16, 2026, 11:35 a.m.