Triple

T15779250
Position Surface form Disambiguated ID Type / Status
Subject Lyon Metro line D E382568 entity
Predicate serves P98 FINISHED
Object Vaise
Vaise is a neighborhood in the 9th arrondissement of Lyon, France, known as a residential and commercial area connected to the city center by Lyon Metro line D.
E1178015 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: Vaise | Statement: [Lyon Metro line D, serves, Vaise]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Vaise
Context triple: [Lyon Metro line D, serves, Vaise]
  • A. Veddesta
    Veddesta is an industrial and commercial area in Järfälla Municipality, northwest of central Stockholm, Sweden.
  • B. Vaako
    Vaako is a ruthless and ambitious Necromonger commander from the science fiction film series "The Chronicles of Riddick."
  • C. Viroinval
    Viroinval is a rural municipality in southern Belgium known for its scenic landscapes, forests, and limestone valleys within the Ardennes region.
  • D. Velkua
    Velkua is a former island municipality in southwestern Finland known for its coastal archipelago landscape in the Baltic Sea.
  • E. Eivissa
    Eivissa is the Catalan name for Ibiza, a popular Mediterranean island in Spain’s Balearic archipelago known for its beaches and nightlife.
  • 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: Vaise
Triple: [Lyon Metro line D, serves, Vaise]
Generated description
Vaise is a neighborhood in the 9th arrondissement of Lyon, France, known as a residential and commercial area connected to the city center by Lyon Metro line D.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Vaise
Target entity description: Vaise is a neighborhood in the 9th arrondissement of Lyon, France, known as a residential and commercial area connected to the city center by Lyon Metro line D.
  • A. Veddesta
    Veddesta is an industrial and commercial area in Järfälla Municipality, northwest of central Stockholm, Sweden.
  • B. Vaako
    Vaako is a ruthless and ambitious Necromonger commander from the science fiction film series "The Chronicles of Riddick."
  • C. Viroinval
    Viroinval is a rural municipality in southern Belgium known for its scenic landscapes, forests, and limestone valleys within the Ardennes region.
  • D. Velkua
    Velkua is a former island municipality in southwestern Finland known for its coastal archipelago landscape in the Baltic Sea.
  • E. Eivissa
    Eivissa is the Catalan name for Ibiza, a popular Mediterranean island in Spain’s Balearic archipelago known for its beaches and nightlife.
  • 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_69d86da09a10819082fe9797b23e4664 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e053fea90081908e3fe4f91475bead completed April 16, 2026, 3:14 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff9987140c8190a50da103905a7930 completed May 9, 2026, 8:31 p.m.
NEDg Description generation batch_69ff9a70eafc8190a2e9c87150267c4a completed May 9, 2026, 8:34 p.m.
NED2 Entity disambiguation (via description) batch_69ff9acbd2b481908b9d415e26d0db81 completed May 9, 2026, 8:36 p.m.
Created at: April 10, 2026, 4:48 a.m.