Triple
T7766231
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Port of Savona |
E176153
|
entity |
| Predicate | serves |
P98
|
FINISHED |
| Object | city of Savona |
E320914
|
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: city of Savona | Statement: [Port of Savona, serves, city of Savona]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: city of Savona Context triple: [Port of Savona, serves, city of Savona]
-
A.
Port of Savona
The Port of Savona is a major commercial and passenger seaport in northwestern Italy, serving as an important hub for Mediterranean trade and cruise traffic.
-
B.
Savona
chosen
Savona is a coastal city and port in the Liguria region of northwestern Italy, known historically as a strategic maritime center on the Italian Riviera.
-
C.
Genoa
Genoa is a historic port city in northwestern Italy known for its significant maritime heritage, trade, and role as a major economic hub on the Ligurian coast.
-
D.
Genoa
Genoa is the codename for AMD’s fourth-generation EPYC server processors based on the Zen 4 architecture and the SP5 platform.
-
E.
Livorno
Livorno is a port city on Italy’s western coast, historically notable for its diverse communities and significant Jewish population.
- 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_69c69962923c8190ac74d28b4f9fe0a0 |
completed | March 27, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69c7043451bc8190a76ee066b779b7d7 |
completed | March 27, 2026, 10:27 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c8c7e1a1408190a802d4f4afb8dd05 |
completed | March 29, 2026, 6:34 a.m. |
Created at: March 27, 2026, 4:10 p.m.