Triple

T15299395
Position Surface form Disambiguated ID Type / Status
Subject M2 (Lausanne Metro) E365743 entity
Predicate servesStation P839 FINISHED
Object Montelly
Montelly is a metro station on Lausanne’s M2 line in Switzerland, serving the local neighborhood within the city’s urban transit network.
E1149178 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: Montelly | Statement: [M2 (Lausanne Metro), servesStation, Montelly]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Montelly
Context triple: [M2 (Lausanne Metro), servesStation, Montelly]
  • A. Myles Mitchell
    Myles Mitchell is the stepson of Dee Mitchell, a character from the television series "Moesha."
  • B. Ceionius
    Ceionius was an ancient Roman family name (nomen gentilicium) associated with the aristocratic gens Ceionia.
  • C. Terrell
    Terrell is a small city in Kaufman County, Texas, known as an outlying suburb of the Dallas–Fort Worth metropolitan area.
  • D. Terrell
    Terrell is a masculine given name most notably associated with American athletes, particularly in professional football and basketball.
  • E. Kellen
    Kellen is a masculine given name most notably associated with former NFL tight end and Hall of Famer Kellen Winslow.
  • 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: Montelly
Triple: [M2 (Lausanne Metro), servesStation, Montelly]
Generated description
Montelly is a metro station on Lausanne’s M2 line in Switzerland, serving the local neighborhood within the city’s urban transit network.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Montelly
Target entity description: Montelly is a metro station on Lausanne’s M2 line in Switzerland, serving the local neighborhood within the city’s urban transit network.
  • A. Myles Mitchell
    Myles Mitchell is the stepson of Dee Mitchell, a character from the television series "Moesha."
  • B. Ceionius
    Ceionius was an ancient Roman family name (nomen gentilicium) associated with the aristocratic gens Ceionia.
  • C. Terrell
    Terrell is a small city in Kaufman County, Texas, known as an outlying suburb of the Dallas–Fort Worth metropolitan area.
  • D. Terrell
    Terrell is a masculine given name most notably associated with American athletes, particularly in professional football and basketball.
  • E. Kellen
    Kellen is a masculine given name most notably associated with former NFL tight end and Hall of Famer Kellen Winslow.
  • 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_69d85a113ee881908e297a1d38dd79fa completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e03686bfb8819080ba0caae652170a completed April 16, 2026, 1:08 a.m.
NED1 Entity disambiguation (via context triple) batch_69feef8513a08190b2d2a7dde85dd43d completed May 9, 2026, 8:25 a.m.
NEDg Description generation batch_69fef23de4688190beeb59ef43891e3d completed May 9, 2026, 8:37 a.m.
NED2 Entity disambiguation (via description) batch_69fef2d8fe04819084bb3deb6859d746 completed May 9, 2026, 8:39 a.m.
Created at: April 10, 2026, 3:15 a.m.