Triple

T22300176
Position Surface form Disambiguated ID Type / Status
Subject Paddington Square E551232 entity
Predicate structuralEngineer P616 FINISHED
Object WSP Global 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: WSP Global | Statement: [Paddington Square, structuralEngineer, WSP Global]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: WSP Global
Context triple: [Paddington Square, structuralEngineer, WSP Global]
  • A. WSP Global chosen
    WSP Global is a Canadian-based multinational professional services firm specializing in engineering, design, and consulting for infrastructure, environmental, building, and transportation projects worldwide.
  • B. Louis Berger Group
    Louis Berger Group is a global engineering and infrastructure consulting firm known for designing and managing major transportation and civil works projects worldwide.
  • C. Ramboll
    Ramboll is a global engineering, design, and consultancy company known for delivering innovative and sustainable solutions in buildings, transport, environment, energy, and infrastructure projects.
  • D. WSP
    WSP is the station code for Weesperplein, a metro station in Amsterdam, Netherlands.
  • E. WSP
    WSP is the official station code used to identify Weesp railway station in the Netherlands.
  • 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_69e11e46c0188190800181a4233f28fe completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f1572399148190853c4e91fcf9f38c completed April 29, 2026, 12:56 a.m.
Created at: April 16, 2026, 8:41 p.m.