Triple

T783945
Position Surface form Disambiguated ID Type / Status
Subject Corsica E16558 entity
Predicate hasPort P35 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: [Corsica, hasPort, Calvi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Calvi
Context triple: [Corsica, hasPort, 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. Livorno
    Livorno is a port city on Italy’s western coast, historically notable for its diverse communities and significant Jewish population.
  • C. Viareggio
    Viareggio is a coastal city in Tuscany, Italy, renowned for its seaside resorts and famous annual Carnival.
  • D. Porto Ercole
    Porto Ercole is a coastal village on Italy’s Monte Argentario peninsula, known as a historic Tuscan port and the place where the painter Caravaggio died.
  • E. San Savino
    San Savino is a small locality within the municipality of Predappio in the Emilia-Romagna region of northern Italy.
  • 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_69a4936ad1fc81908f190208059ccf78 completed March 1, 2026, 7:28 p.m.
NER Named-entity recognition batch_69a4a769dc6481908f12e872f997acf3 completed March 1, 2026, 8:54 p.m.
NED1 Entity disambiguation (via context triple) batch_69ac7f211bf88190bd6f791894ece41a completed March 7, 2026, 7:40 p.m.
Created at: March 1, 2026, 7:37 p.m.