Triple
T18998592
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cannobio |
E464885
|
entity |
| Predicate | hasSubdivision |
P747
|
FINISHED |
| Object |
Socragno
Socragno is a small locality or frazione within the municipality of Cannobio in the Piedmont region of northern Italy.
|
E1353177
|
NE FINISHED |
How this triple was built (4 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: Socragno | Statement: [Cannobio, hasSubdivision, Socragno]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Socragno Context triple: [Cannobio, hasSubdivision, Socragno]
-
A.
Segusio
Segusio was an ancient Roman town in the Alps, strategically located on key transalpine routes in what is now Susa, Italy.
-
B.
Reola
Reola is a village in Tartu County, Estonia, situated just south of the city of Tartu.
-
C.
Sarsina
Sarsina is a historic town in Italy’s Emilia-Romagna region, known as the birthplace of the Roman playwright Plautus and for its ancient Roman and medieval heritage.
-
D.
Rapagnano
Rapagnano is a small Italian municipality in the Marche region known for its historic hilltop setting and traditional rural character.
-
E.
Saracena
Saracena is a historic town and comune in the Calabria region of southern Italy, known for its medieval architecture and traditional Moscato di Saracena wine.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Socragno Triple: [Cannobio, hasSubdivision, Socragno]
Generated description
Socragno is a small locality or frazione within the municipality of Cannobio in the Piedmont region of northern Italy.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Socragno Target entity description: Socragno is a small locality or frazione within the municipality of Cannobio in the Piedmont region of northern Italy.
-
A.
Segusio
Segusio was an ancient Roman town in the Alps, strategically located on key transalpine routes in what is now Susa, Italy.
-
B.
Reola
Reola is a village in Tartu County, Estonia, situated just south of the city of Tartu.
-
C.
Sarsina
Sarsina is a historic town in Italy’s Emilia-Romagna region, known as the birthplace of the Roman playwright Plautus and for its ancient Roman and medieval heritage.
-
D.
Rapagnano
Rapagnano is a small Italian municipality in the Marche region known for its historic hilltop setting and traditional rural character.
-
E.
Saracena
Saracena is a historic town and comune in the Calabria region of southern Italy, known for its medieval architecture and traditional Moscato di Saracena wine.
- F. None of above. chosen
Provenance (5 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_69d8dd01a56c81909694a128c66b21d7 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5d6838f4481909b265e29964b0dca |
completed | April 20, 2026, 7:32 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a05b459c36c8190a9d8831fdb7f8b93 |
completed | May 14, 2026, 11:39 a.m. |
| NEDg | Description generation | batch_6a05b6491f608190a72d40867f4a2ca3 |
completed | May 14, 2026, 11:47 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a05b6cd93c88190a5400e86a14771f1 |
completed | May 14, 2026, 11:49 a.m. |
Created at: April 10, 2026, 12:01 p.m.