Triple

T28858766
Position Surface form Disambiguated ID Type / Status
Subject first-generation Audi A4 E728805 entity
Predicate introducedAudiDesignLanguage P114288 FINISHED
Object modern Audi compact executive sedan design LITERAL 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: modern Audi compact executive sedan design | Statement: [first-generation Audi A4, introducedAudiDesignLanguage, modern Audi compact executive sedan design]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: introducedAudiDesignLanguage
Context triple: [first-generation Audi A4, introducedAudiDesignLanguage, modern Audi compact executive sedan design]
  • A. introducedDesignLanguage chosen
    Indicates that an entity initiated or brought a particular design language into use or public awareness.
  • B. hasDesignLanguage
    Indicates that one entity employs, follows, or is characterized by the design language specified by another entity.
  • C. engineIntroduced
    Indicates that a particular engine was first introduced or brought into use at a specific time or in a specific context.
  • D. introducedModernStylingComparedTo
    Indicates that one entity brought in or established a more contemporary or updated style relative to another entity.
  • E. introducedSilhouette
    Indicates that one entity caused another entity to first appear or be presented in outline or partial form, rather than in full detail.
  • F. None of above.

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_69f0319f4e5481909e4c439dbe8be940 completed April 28, 2026, 4:03 a.m.
NER Named-entity recognition batch_69f791cc969c8190bf187d6031a030d5 completed May 3, 2026, 6:19 p.m.
PD Predicate disambiguation batch_69f791033d288190b118029fe412b9c9 completed May 3, 2026, 6:16 p.m.
Created at: April 28, 2026, 6:46 a.m.