Triple

T21806720
Position Surface form Disambiguated ID Type / Status
Subject Ian Clark Wood E538368 entity
Predicate employer P7 FINISHED
Object Wood 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: Wood Group | Statement: [Ian Clark Wood, employer, Wood Group]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Wood Group
Context triple: [Ian Clark Wood, employer, Wood Group]
  • A. Wood Group chosen
    Wood Group is a global engineering and consulting company serving the energy and industrial sectors with project, operations, and environmental services.
  • B. Petroleum Group
    The Petroleum Group is a specialist division of the Geological Society of London focused on the study and professional exchange of knowledge related to petroleum geoscience and hydrocarbon exploration.
  • C. Halliburton
    Halliburton is a major American multinational corporation that provides products and services to the oil and gas industry worldwide.
  • D. Noble Corporation
    Noble Corporation is a major offshore drilling contractor that provides oil and gas exploration and production services worldwide.
  • E. Aker BP
    Aker BP is a Norwegian oil and gas exploration and production company and one of the largest independent operators on the Norwegian Continental Shelf.
  • 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_69e0c473f0f8819086c9d1b4a143bd67 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69f07803b4888190af06bf7a90198f60 completed April 28, 2026, 9:04 a.m.
Created at: April 16, 2026, 6:53 p.m.