Triple

T6609975
Position Surface form Disambiguated ID Type / Status
Subject Runway 07/25 E149211 entity
Predicate servesCity P82 FINISHED
Object Charleroi E95883 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: Charleroi | Statement: [Runway 07/25, servesCity, Charleroi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Charleroi
Context triple: [Runway 07/25, servesCity, Charleroi]
  • A. Charleroi chosen
    Charleroi is a major industrial city in the Walloon region of Belgium, historically important as a fortified stronghold and later as a center of coal mining and heavy industry.
  • B. Tervuren
    Tervuren is a municipality in Flemish Brabant, Belgium, known for its historic park, royal connections, and the Royal Museum for Central Africa.
  • C. Mechelen
    Mechelen is a historic city in the Flemish region of Belgium, known for its rich architectural heritage, medieval center, and prominent role in the Low Countries’ political and religious history.
  • D. Liège
    Liège is a major city in eastern Belgium known for its industrial heritage, vibrant cultural scene, and position along the Meuse River.
  • E. Vilvoorde
    Vilvoorde is a city in the Flemish Region of Belgium, located just north of Brussels and known as part of the capital’s broader metropolitan area.
  • 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_69c687ebc680819094caf71faba2efe2 completed March 27, 2026, 1:36 p.m.
NER Named-entity recognition batch_69c6af3301dc819082d427675c36aaa6 completed March 27, 2026, 4:24 p.m.
NED1 Entity disambiguation (via context triple) batch_69c7e4f308048190a5c42022e3f9e855 completed March 28, 2026, 2:25 p.m.
Created at: March 27, 2026, 1:57 p.m.