Triple

T18181595
Position Surface form Disambiguated ID Type / Status
Subject Sir Michael Marshall E435297 entity
Predicate employer P7 FINISHED
Object Marshall Group 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: Marshall Group | Statement: [Sir Michael Marshall, employer, Marshall Group]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Marshall Group
Context triple: [Sir Michael Marshall, employer, Marshall Group]
  • A. Marshall Group chosen
    Marshall Group is a British aerospace and defense company based in Cambridge, known for its aviation services, engineering, and property businesses.
  • B. Bell-Mason Group
    Bell-Mason Group is a consulting and advisory firm best known for developing the Bell-Mason Diagnostic, a framework for assessing and guiding the growth of technology startups and ventures.
  • C. Wilson Group
    The Wilson Group is a cluster of galaxies in the constellation of Centaurus that includes Mount Wilson as one of its notable members.
  • D. West Group
    West Group was a major American legal publishing company best known for producing comprehensive case law reporters and legal research materials used by lawyers and courts.
  • E. The Walsh Group
    The Walsh Group is a major U.S.-based construction and general contracting firm known for large-scale infrastructure, building, and transportation projects.
  • 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_69d8b90c7ec081909b4694ccecb449c6 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4dffb3bc88190a627be9c444d5c7d completed April 19, 2026, 2 p.m.
Created at: April 10, 2026, 10:31 a.m.