Triple

T8808699
Position Surface form Disambiguated ID Type / Status
Subject Ford CD2 platform E209599 entity
Predicate basedOn P98 FINISHED
Object Mazda GF platform E727430 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 GF platform | Statement: [Ford CD2 platform, basedOn, Mazda GF platform]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mazda GF platform
Context triple: [Ford CD2 platform, basedOn, Mazda GF platform]
  • A. Mazda BK platform
    The Mazda BK platform is a compact car architecture used primarily for the Mazda3, developed in collaboration with Ford as part of a shared global small-car chassis program.
  • B. Mazda G platform (first generation) chosen
    The first-generation Mazda G platform is a mid-size car architecture developed by Mazda that underpinned the original Mazda6 and related models in the early 2000s.
  • C. Nissan FF-L platform
    The Nissan FF-L platform is a front-wheel-drive-based automotive architecture developed by Nissan for its mid-size crossover SUVs and related vehicles.
  • D. Nissan B platform
    The Nissan B platform is a small car architecture used by Nissan and its partners as the basis for various subcompact and compact vehicles.
  • E. Nissan CMF-C platform
    The Nissan CMF-C platform is a modular vehicle architecture co-developed within the Renault–Nissan–Mitsubishi Alliance for compact cars and crossovers, enabling shared components, improved efficiency, and advanced safety and technology 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_69ca8363f3308190a47e3f1ebd51f613 completed March 30, 2026, 2:06 p.m.
NER Named-entity recognition batch_69cc5fd4cbec8190a929d4e60da8ad65 completed March 31, 2026, 11:59 p.m.
NED1 Entity disambiguation (via context triple) batch_69cf6fa0e4308190bd01c2d107c8c02d completed April 3, 2026, 7:43 a.m.
Created at: March 30, 2026, 6:45 p.m.