Triple
T22783100
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Province of Vercelli |
E563890
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object | Santhià |
—
|
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: Santhià | Statement: [Province of Vercelli, contains, Santhià]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Santhià Context triple: [Province of Vercelli, contains, Santhià]
-
A.
Santhià
chosen
Santhià is a town in the Piedmont region of northwestern Italy, known historically as the place where Duke Francesco I d'Este died.
-
B.
Nonza
Nonza is a picturesque coastal village on the island of Corsica in France, known for its dramatic cliffside setting and distinctive black pebble beach.
-
C.
Santena
Santena is a small town in the Piedmont region of northern Italy, known for its historical association with statesman Camillo Benso, Count of Cavour.
-
D.
Santanyí
Santanyí is a picturesque coastal town in southeastern Mallorca, Spain, known for its traditional stone architecture, weekly markets, and nearby sandy coves.
-
E.
Sierroz
Sierroz is a river in eastern France that serves as one of the tributaries feeding into Lac du Bourget.
- 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_69e2455500788190b4b33030461f3bbd |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f17c2ee4e88190951afb2abe69009f |
completed | April 29, 2026, 3:34 a.m. |
Created at: April 17, 2026, 3:29 p.m.