Triple

T19946975
Position Surface form Disambiguated ID Type / Status
Subject Levante S E479445 entity
Predicate relatedModel P37 FINISHED
Object Levante NE NERFINISHED

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: Levante | Statement: [Levante S, relatedModel, Levante]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Levante
Context triple: [Levante S, relatedModel, Levante]
  • A. Levante chosen
    Levante is a luxury midsize SUV model produced by the Italian automaker Maserati, known for its sporty performance and upscale design.
  • B. Levante
    Levante is a Spanish professional football club based in Valencia that competes in the country’s football league system.
  • C. Levante
    Levante is a strong, warm easterly wind that blows across the Strait of Gibraltar and southern Spain, often bringing dry conditions and rough seas.
  • D. Costa Blanca
    Costa Blanca is a popular Mediterranean coastal region in Spain’s Alicante province, renowned for its sandy beaches, resort towns, and sunny climate.
  • E. Marina Alta
    Marina Alta is a coastal comarca in the northern part of Spain’s Alicante province, known for its Mediterranean beaches, rugged landscapes, and tourism centered around towns like Dénia and Jávea.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8e522a17c819095165d4d24939fd8 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e65a68a32c8190ac9601db98594465 completed April 20, 2026, 4:55 p.m.
Created at: April 10, 2026, 1:54 p.m.