Triple

T16303158
Position Surface form Disambiguated ID Type / Status
Subject Mazda 787B E395839 entity
Predicate team P3756 FINISHED
Object Mazda Sport E1206203 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: Mazda Sport | Statement: [Mazda 787B, team, Mazda Sport]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mazda Sport
Context triple: [Mazda 787B, team, Mazda Sport]
  • A. Mazda Speed chosen
    Mazda Speed is Mazda's motorsport and high-performance division responsible for developing and running the brand’s racing cars and performance projects.
  • B. Mazda MX series
    The Mazda MX series is a lineup of Mazda’s sporty, performance-oriented vehicles that includes models like the MX-5 Miata and MX-6.
  • C. Mazda SC
    Mazda SC was a Japanese company football club owned by Mazda that later evolved into the professional J.League team Sanfrecce Hiroshima.
  • D. Mazda Axela
    The Mazda Axela is the name used in Japan for the Mazda3, a popular compact car known for its sporty handling and stylish design.
  • E. Mazda Cosmo Sport
    The Mazda Cosmo Sport is a pioneering late-1960s Japanese sports car best known as one of the first production vehicles powered by a Wankel rotary engine.
  • 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_69d87f23bb088190a16fbb91a1957ea5 completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e25e35157481909e5604b7dae7a2a2 completed April 17, 2026, 4:22 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00260151908190b83f700a1c7c6419 completed May 10, 2026, 6:30 a.m.
Created at: April 10, 2026, 5:06 a.m.