Triple
T16140086
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chemins de fer de la Corse |
E391629
|
entity |
| Predicate | connectsCity |
P4245
|
FINISHED |
| Object | Calvi |
E136975
|
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: Calvi | Statement: [Chemins de fer de la Corse, connectsCity, Calvi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Calvi Context triple: [Chemins de fer de la Corse, connectsCity, Calvi]
-
A.
Calvi
chosen
Calvi is a coastal town and popular tourist destination on the northwest coast of the French island of Corsica, known for its historic citadel and scenic bay.
-
B.
Calvi
Calvi is a small Italian municipality located in the Campania region within the Province of Benevento.
-
C.
Quarrata
Quarrata is a Tuscan town in central Italy known for its furniture industry and proximity to the cities of Pistoia and Florence.
-
D.
Bordighera
Bordighera is a coastal town on the Italian Riviera in Liguria, known for its mild climate, palm-lined seafront, and historic appeal as a 19th-century resort.
-
E.
Follonica
Follonica is a coastal town and popular seaside resort in Tuscany, Italy, known for its sandy beaches along the Tyrrhenian Sea.
- 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_69d87f1bb0988190b490d273dbf3fd03 |
completed | April 10, 2026, 4:39 a.m. |
| NER | Named-entity recognition | batch_69e21a07b7908190b4e1ec57f60a9274 |
completed | April 17, 2026, 11:31 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a005809cbf08190b35f2c820793163c |
completed | May 10, 2026, 10:03 a.m. |
Created at: April 10, 2026, 5:01 a.m.