Triple

T6211124
Position Surface form Disambiguated ID Type / Status
Subject CDG Terminal 2 E138870 entity
Predicate operatedBy P86 FINISHED
Object Groupe ADP E11760 NE FINISHED

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: Groupe ADP | Statement: [CDG Terminal 2, operatedBy, Groupe ADP]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Groupe ADP
Context triple: [CDG Terminal 2, operatedBy, Groupe ADP]
  • A. Groupe ADP chosen
    Groupe ADP is a major French airport management company that owns and operates the Paris-area airports and provides aviation and related services worldwide.
  • B. Deloitte
    Deloitte is one of the world’s largest professional services firms, providing audit, consulting, tax, and advisory services to clients globally.
  • C. Ernst & Young
    Ernst & Young is a global professional services firm, known as one of the "Big Four" accounting organizations, providing audit, tax, consulting, and advisory services to clients worldwide.
  • D. Accenture
    Accenture is a global professional services company specializing in consulting, technology, and outsourcing solutions for businesses and governments worldwide.
  • E. Omnicom Group
    Omnicom Group is a global marketing and communications holding company that owns numerous leading advertising, media, and public relations agencies worldwide.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69c008ada364819096c9e92c74d639b5 completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c062896f3881909f264bb45badc5d0 completed March 22, 2026, 9:43 p.m.
NED1 Entity disambiguation (via context triple) batch_69c20da55e3c81909a61471b38e88894 completed March 24, 2026, 4:05 a.m.
Created at: March 22, 2026, 4:21 p.m.