Triple
T11468184
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Erba |
E271830
|
entity |
| Predicate | partOf |
P40
|
FINISHED |
| Object | Brianza |
E915867
|
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: Brianza | Statement: [Erba, partOf, Brianza]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Brianza Context triple: [Erba, partOf, Brianza]
-
A.
Brianza
chosen
Brianza is a hilly, densely populated area in northern Italy’s Lombardy region, known for its industrial towns, affluent suburbs, and proximity to Milan.
-
B.
Lombardy
Lombardy is a populous and economically powerful region in northern Italy, known for its capital Milan and its role as a major European hub for finance, fashion, and industry.
-
C.
Canavese area
The Canavese area is a historical and geographical region in northern Piedmont, Italy, known for its rolling hills, medieval castles, vineyards, and proximity to the Alps.
-
D.
Massa Lombarda
Massa Lombarda is a small Italian town in the Emilia-Romagna region, known for its agricultural traditions and location within the fertile Po Valley.
-
E.
Valsesia
Valsesia is a scenic alpine valley in Italy’s Piedmont region, known for its mountain landscapes, outdoor sports, and traditional villages.
- 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_69d6aae0c8d881908a5a360c0be3242e |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d822f74144819094479690c8151073 |
completed | April 9, 2026, 10:06 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e5e9429a308190810b485708d28617 |
completed | April 20, 2026, 8:52 a.m. |
Created at: April 8, 2026, 9:35 p.m.