Triple

T1770154
Position Surface form Disambiguated ID Type / Status
Subject Thalys E38855 entity
Predicate primaryRoute P6298 FINISHED
Object Brussels–Cologne
Brussels–Cologne is a major international high-speed rail corridor linking Belgium’s capital with the German city of Cologne.
 E205623 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: Brussels–Cologne | Statement: [Thalys, primaryRoute, Brussels–Cologne]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Brussels–Cologne
Context triple: [Thalys, primaryRoute, Brussels–Cologne]
  • A. Paris–Brussels
    Paris–Brussels is a major international high-speed rail corridor linking the capitals of France and Belgium.
  • B. Brussels–Amsterdam
    Brussels–Amsterdam is a major international high-speed rail route connecting the capitals of Belgium and the Netherlands.
  • C. Paris–Amsterdam
    Paris–Amsterdam is a major international high-speed rail route linking the capitals of France and the Netherlands.
  • D. Intercity Brussels
    Intercity Brussels is an international high-speed train service connecting the Netherlands with Brussels in Belgium.
  • E. Bruxelles-Midi / Brussel-Zuid
    Bruxelles-Midi / Brussel-Zuid is the main international and long-distance railway hub of Brussels, serving high-speed trains like Eurostar and Thalys as well as extensive domestic services.
  • 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: Brussels–Cologne
Triple: [Thalys, primaryRoute, Brussels–Cologne]
Generated description
Brussels–Cologne is a major international high-speed rail corridor linking Belgium’s capital with the German city of Cologne.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Brussels–Cologne
Target entity description: Brussels–Cologne is a major international high-speed rail corridor linking Belgium’s capital with the German city of Cologne.
  • A. Paris–Brussels
    Paris–Brussels is a major international high-speed rail corridor linking the capitals of France and Belgium.
  • B. Brussels–Amsterdam
    Brussels–Amsterdam is a major international high-speed rail route connecting the capitals of Belgium and the Netherlands.
  • C. Paris–Amsterdam
    Paris–Amsterdam is a major international high-speed rail route linking the capitals of France and the Netherlands.
  • D. Intercity Brussels
    Intercity Brussels is an international high-speed train service connecting the Netherlands with Brussels in Belgium.
  • E. Bruxelles-Midi / Brussel-Zuid
    Bruxelles-Midi / Brussel-Zuid is the main international and long-distance railway hub of Brussels, serving high-speed trains like Eurostar and Thalys as well as extensive domestic services.
  • 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_69a8862e61708190af97b9838cc3f5de completed March 4, 2026, 7:21 p.m.
NER Named-entity recognition batch_69aa648eb9488190b1be2d2b6d259634 completed March 6, 2026, 5:22 a.m.
NED1 Entity disambiguation (via context triple) batch_69adc9a14a18819090b83b3d10304c74 completed March 8, 2026, 7:10 p.m.
NEDg Description generation batch_69adcaed1f788190b14c3e2d2c3036d9 completed March 8, 2026, 7:15 p.m.
NED2 Entity disambiguation (via description) batch_69adcbee97e88190adc1315c0a5013ab completed March 8, 2026, 7:20 p.m.
Created at: March 4, 2026, 7:31 p.m.