Triple

T4174328
Position Surface form Disambiguated ID Type / Status
Subject Hainaut E86438 entity
Predicate hasCity P316 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: [Hainaut, hasCity, Charleroi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Charleroi
Context triple: [Hainaut, hasCity, 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. 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.
  • C. Liège
    Liège is a major city in eastern Belgium known for its industrial heritage, vibrant cultural scene, and position along the Meuse River.
  • D. 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.
  • E. Binche
    Binche is a historic town in the Walloon region of Belgium, renowned for its well-preserved medieval architecture and its UNESCO-recognized Carnival of Binche.
  • 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_69aed93de98c8190ad838ce507b77c8a completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69af02e7d30081909774a3e2a2132d6a completed March 9, 2026, 5:27 p.m.
NED1 Entity disambiguation (via context triple) batch_69bfe61a2cd8819089ea67309d284be4 completed March 22, 2026, 12:52 p.m.
Created at: March 9, 2026, 3:45 p.m.