Triple

T213509
Position Surface form Disambiguated ID Type / Status
Subject Corsicans E4767 entity
Predicate capitalRegion P3877 FINISHED
Object Ajaccio E22361 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: Ajaccio | Statement: [Corsicans, capitalRegion, Ajaccio]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ajaccio
Context triple: [Corsicans, capitalRegion, Ajaccio]
  • A. Ajaccio chosen
    Ajaccio is a coastal city on the French island of Corsica, best known as the birthplace of Napoleon Bonaparte and now a popular Mediterranean tourist destination.
  • B. Marseille
    Marseille is a historic Mediterranean port city in southern France known for its diverse culture, maritime heritage, and role as a major economic hub.
  • C. Avignon
    Avignon is a historic city in southeastern France renowned for its medieval architecture, including the Palais des Papes, and its role as a former seat of the papacy.
  • D. Sanremo
    Sanremo is a coastal city on Italy’s Ligurian Riviera, known as a historic resort destination and host of the annual Sanremo Music Festival.
  • E. Ventimiglia
    Ventimiglia is a coastal town in northwestern Italy’s Liguria region, known as a key gateway between Italy and France and for its historic center and Mediterranean beaches.
  • 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_69a2575cb1dc8190a01ad332426dc339 completed Feb. 28, 2026, 2:47 a.m.
NER Named-entity recognition batch_69a25c32ae208190a03d504ef43ea659 completed Feb. 28, 2026, 3:08 a.m.
NED1 Entity disambiguation (via context triple) batch_69a44cb1bfe48190b8b7523b95d4a099 completed March 1, 2026, 2:26 p.m.
Created at: Feb. 28, 2026, 2:52 a.m.