Triple

T22886484
Position Surface form Disambiguated ID Type / Status
Subject The Bow E567616 entity
Predicate structuralEngineer P616 FINISHED
Object Halcrow Yolles 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: Halcrow Yolles | Statement: [The Bow, structuralEngineer, Halcrow Yolles]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Halcrow Yolles
Context triple: [The Bow, structuralEngineer, Halcrow Yolles]
  • A. Maunsell
    Maunsell was a prominent international engineering and consulting firm known for its work on major infrastructure and transportation projects.
  • B. Halcrow Group chosen
    Halcrow Group was a British engineering consultancy firm known for its work on major infrastructure and transportation projects worldwide.
  • C. Brunel Construction Centre
    Brunel Construction Centre is a specialist vocational campus of Kirklees College focused on training in construction and related trades.
  • D. Brent and Harrow
    Brent and Harrow is a London Assembly constituency in northwest London that covers the boroughs of Brent and Harrow and elects a representative to the London Assembly.
  • E. Wardrop Engineering
    Wardrop Engineering is a Canadian engineering consulting firm known for its role in designing major infrastructure projects such as Winnipeg’s Esplanade Riel pedestrian bridge.
  • 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_69e2458a92ec81908fc1cd5f6407d2ab completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f17fc1e3408190833a062afbea509d completed April 29, 2026, 3:49 a.m.
Created at: April 17, 2026, 3:40 p.m.