Triple

T21538778
Position Surface form Disambiguated ID Type / Status
Subject Second Severn Crossing E531420 entity
Predicate designer P184 FINISHED
Object SETRA 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: SETRA | Statement: [Second Severn Crossing, designer, SETRA]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: SETRA
Context triple: [Second Severn Crossing, designer, SETRA]
  • A. SETRA chosen
    SETRA is a French public engineering agency specializing in the design, expertise, and technical support of major transport infrastructure, particularly bridges and roads.
  • B. Siemens-Duewag U2
    The Siemens-Duewag U2 is a high-floor light rail vehicle widely used in North American transit systems, notably in early expansions of Calgary’s CTrain network.
  • C. Electrostar
    Electrostar is a widely used family of British electric multiple-unit commuter trains built by Bombardier for suburban and regional services.
  • D. Suter
    Suter is a surname of Germanic origin, often associated with individuals of Swiss or German heritage.
  • E. Siemens Venture long-distance coach
    The Siemens Venture long-distance coach is a modern, intercity passenger railcar designed by Siemens for enhanced comfort, accessibility, and efficiency on long-distance routes in North America.
  • 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_69e0c45e5b8881908ac18fc2f493b114 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69ee9d10a2888190bc4e502a829c76a4 completed April 26, 2026, 11:17 p.m.
Created at: April 16, 2026, 6:27 p.m.