Triple

T23236850
Position Surface form Disambiguated ID Type / Status
Subject British Rail Class 390 E581322 entity
Predicate formerLivery P21786 FINISHED
Object Virgin Trains red and silver livery 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: Virgin Trains red and silver livery | Statement: [British Rail Class 390, formerLivery, Virgin Trains red and silver livery]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: formerLivery
Context triple: [British Rail Class 390, formerLivery, Virgin Trains red and silver livery]
  • A. hasLivery chosen
    Indicates that one entity bears or displays the distinctive colors, markings, or branding (livery) associated with another entity.
  • B. liveryInspiredBy
    Indicates that one livery’s design, colors, or overall appearance is based on, influenced by, or pays homage to another livery.
  • C. liveryFeature
    Indicates a characteristic or design element that is part of a specific livery or external appearance scheme.
  • D. liveryColors
    Indicates the specific set of colors used as the official or characteristic color scheme associated with an entity (such as a brand, organization, or vehicle).
  • E. hasFormerLogo
    Indicates that an entity is associated with a logo it used in the past but no longer uses.
  • 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_69e2460556f88190be1744a84a84173f completed April 17, 2026, 2:39 p.m.
NER Named-entity recognition batch_69f192e98dec8190a23385600bed9ae0 completed April 29, 2026, 5:11 a.m.
PD Predicate disambiguation batch_69effcdadec0819092ec1749ee453b4e completed April 28, 2026, 12:18 a.m.
Created at: April 17, 2026, 4:09 p.m.