Triple

T1713739
Position Surface form Disambiguated ID Type / Status
Subject German-speaking Community E37242 entity
Predicate capital P234 FINISHED
Object Eupen
Eupen is a town in eastern Belgium that serves as the administrative center of the country’s German-speaking Community.
 E300219 NE FINISHED

How this triple was built (4 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: Eupen | Statement: [German-speaking Community, capital, Eupen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Eupen
Context triple: [German-speaking Community, capital, Eupen]
  • A. 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.
  • B. 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.
  • C. Hasselt
    Hasselt is a historic small city in the Dutch province of Overijssel, known for its medieval center and canals.
  • D. Hasselt
    Hasselt is a city in northeastern Belgium that serves as the capital of the province of Limburg in the Flemish region.
  • E. Oudenarde
    Oudenarde (Oudenaarde) is a historic town in East Flanders, Belgium, known for its medieval architecture, tapestry production, and role in early modern European conflicts.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Eupen
Triple: [German-speaking Community, capital, Eupen]
Generated description
Eupen is a town in eastern Belgium that serves as the administrative center of the country’s German-speaking Community.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Eupen
Target entity description: Eupen is a town in eastern Belgium that serves as the administrative center of the country’s German-speaking Community.
  • A. 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.
  • B. 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.
  • C. Hasselt
    Hasselt is a historic small city in the Dutch province of Overijssel, known for its medieval center and canals.
  • D. Hasselt
    Hasselt is a city in northeastern Belgium that serves as the capital of the province of Limburg in the Flemish region.
  • E. Oudenarde
    Oudenarde (Oudenaarde) is a historic town in East Flanders, Belgium, known for its medieval architecture, tapestry production, and role in early modern European conflicts.
  • F. None of above. chosen

Provenance (5 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_69a8861912dc8190931af43b4b9158a7 completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69aa63174b3c8190bd2406c78407be28 completed March 6, 2026, 5:16 a.m.
NED1 Entity disambiguation (via context triple) batch_69afc6200bd08190bd1d9fd3046fca00 completed March 10, 2026, 7:20 a.m.
NEDg Description generation batch_69afc9e306e8819094f24c22a9208fcb completed March 10, 2026, 7:36 a.m.
NED2 Entity disambiguation (via description) batch_69afca4638f8819093b6f5f49a950f52 completed March 10, 2026, 7:37 a.m.
Created at: March 4, 2026, 7:30 p.m.