Triple

T13841807
Position Surface form Disambiguated ID Type / Status
Subject Charles de Gaulle – Étoile E332674 entity
Predicate hasStationCode P1289 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: [Charles de Gaulle – Étoile, hasStationCode, CDG]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: CDG
Context triple: [Charles de Gaulle – Étoile, hasStationCode, 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. CGR
    CGR is the IATA airport code for Campo Grande International Airport in Campo Grande, Brazil.
  • D. BDG
    BDG is a Gabonese political party historically associated with figures such as former Prime Minister Léon Mébiame.
  • E. CGK
    CGK is the IATA airport code for Soekarno–Hatta International Airport, the main international gateway serving Jakarta, Indonesia.
  • 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_69d81c5ba13c8190839315f54768acfd completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de02ae5e4c8190ad85ad2968bc71b2 completed April 14, 2026, 9:02 a.m.
NED1 Entity disambiguation (via context triple) batch_69f7b8f630d081909439e1cdc5d60430 completed May 3, 2026, 9:07 p.m.
Created at: April 9, 2026, 10:13 p.m.