Triple

T16302928
Position Surface form Disambiguated ID Type / Status
Subject Skyactiv-G engine E395834 entity
Predicate usedInModel P25490 FINISHED
Object Mazda CX-9 E396580 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 CX-9 | Statement: [Skyactiv-G engine, usedInModel, Mazda CX-9]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mazda CX-9
Context triple: [Skyactiv-G engine, usedInModel, Mazda CX-9]
  • A. Mazda CX-9 chosen
    The Mazda CX-9 is a mid-size three-row crossover SUV known for its stylish design, upscale interior, and engaging driving dynamics.
  • B. Mazda CX-8
    The Mazda CX-8 is a mid-size three-row crossover SUV known for its efficient performance, refined driving dynamics, and upscale interior.
  • C. Mazda CX-5
    The Mazda CX-5 is a compact crossover SUV known for its stylish design, engaging driving dynamics, and efficient Skyactiv technology.
  • D. Mazda MPV
    The Mazda MPV is a mid-size minivan produced by Mazda, known for its family-friendly three-row seating and practical, versatile interior.
  • E. Acura MDX
    The Acura MDX is a midsize luxury crossover SUV known for its three-row seating, refined ride, and upscale features.
  • 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_69e25e3404288190a7106d62c15c3193 completed April 17, 2026, 4:22 p.m.
NED1 Entity disambiguation (via context triple) batch_6a002da444408190b770055d84060f4d completed May 10, 2026, 7:03 a.m.
Created at: April 10, 2026, 5:06 a.m.