Triple

T23216737
Position Surface form Disambiguated ID Type / Status
Subject British Rail Class 91 E580764 entity
Predicate designedBy P184 FINISHED
Object BREL NE NERFINISHED

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: BREL | Statement: [British Rail Class 91, designedBy, BREL]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: BREL
Context triple: [British Rail Class 91, designedBy, BREL]
  • A. BREL York chosen
    BREL York was a major British railway engineering works in York that built and maintained rolling stock for the national rail network.
  • B. BREL Derby
    BREL Derby was a major British railway engineering works in Derby that built and maintained rolling stock for the UK rail network.
  • C. BRE
    BRE is the three-letter IATA airport code for Bremen Airport in Bremen, Germany.
  • D. BRE
    BRE is the National Rail station code for Brentwood railway station in Essex, England.
  • E. BRE
    BRE is the stock ticker symbol for Brembo, an Italian company renowned worldwide for its high-performance automotive braking systems.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e2460389408190be74f41d217799a9 completed April 17, 2026, 2:38 p.m.
NER Named-entity recognition batch_69f19165949c81908e4d66a8a2b0a25a completed April 29, 2026, 5:04 a.m.
Created at: April 17, 2026, 4:08 p.m.