Triple

T1736186
Position Surface form Disambiguated ID Type / Status
Subject XPG E37923 entity
Predicate relatedTo P37 FINISHED
Object CDG E10902 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: CDG | Statement: [XPG, relatedTo, CDG]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: CDG
Context triple: [XPG, relatedTo, CDG]
  • A. CDG chosen
    CDG is the IATA airport code for Charles de Gaulle Airport, the main international airport serving Paris and one of Europe’s busiest air hubs.
  • B. CDGVAL
    CDGVAL is the automated light-rail shuttle system that links the terminals and key facilities within Paris Charles de Gaulle Airport.
  • C. DGC
    DGC is the United Nations Department of Global Communications, responsible for promoting global awareness and understanding of the UN’s work through strategic communication and public outreach.
  • D. CGF
    CGF is the abbreviation for the Commonwealth Games Federation, the international organization responsible for overseeing and managing the Commonwealth Games and related sporting events.
  • E. DGS
    DGS is the California state agency that provides centralized business, procurement, real estate, and support services to other government departments.
  • 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_69a8861cc6ac8190ac0b2e31ccf62851 completed March 4, 2026, 7:21 p.m.
NER Named-entity recognition batch_69aa63a369048190bae352573f5082f1 completed March 6, 2026, 5:18 a.m.
NED1 Entity disambiguation (via context triple) batch_69ad8b008b7881909ac568af010bcf99 completed March 8, 2026, 2:43 p.m.
Created at: March 4, 2026, 7:30 p.m.