Triple

T21324614
Position Surface form Disambiguated ID Type / Status
Subject Lausanne–Villeneuve railway line E525715 entity
Predicate serves P98 FINISHED
Object Territet
Territet is a lakeside locality in Montreux, Switzerland, known as a scenic stop along the railway route on the shores of Lake Geneva.
 E1477899 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: Territet | Statement: [Lausanne–Villeneuve railway line, serves, Territet]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Territet
Context triple: [Lausanne–Villeneuve railway line, serves, Territet]
  • A. Tetiiv
    Tetiiv is a small town in central Ukraine known for its historical roots and location within Kyiv Oblast.
  • B. Tetnuldi
    Tetnuldi is a prominent peak in the central Caucasus Mountains of Georgia, known for its glaciated slopes and popular ski resort.
  • C. Takudh
    Takudh is an alternative name for the Gwich’in language, an Athabaskan language spoken by the Gwich’in people of northwestern Canada and northeastern Alaska.
  • D. Tergu
    Tergu is a small municipality in the Gallura region of northern Sardinia, Italy, known for its rural setting and historic Romanesque church of Nostra Signora di Tergu.
  • E. Tirico
    Tirico is the surname of American sportscaster Mike Tirico, known for his play-by-play work on major sports broadcasts.
  • 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: Territet
Triple: [Lausanne–Villeneuve railway line, serves, Territet]
Generated description
Territet is a lakeside locality in Montreux, Switzerland, known as a scenic stop along the railway route on the shores of Lake Geneva.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Territet
Target entity description: Territet is a lakeside locality in Montreux, Switzerland, known as a scenic stop along the railway route on the shores of Lake Geneva.
  • A. Tetiiv
    Tetiiv is a small town in central Ukraine known for its historical roots and location within Kyiv Oblast.
  • B. Tetnuldi
    Tetnuldi is a prominent peak in the central Caucasus Mountains of Georgia, known for its glaciated slopes and popular ski resort.
  • C. Takudh
    Takudh is an alternative name for the Gwich’in language, an Athabaskan language spoken by the Gwich’in people of northwestern Canada and northeastern Alaska.
  • D. Tergu
    Tergu is a small municipality in the Gallura region of northern Sardinia, Italy, known for its rural setting and historic Romanesque church of Nostra Signora di Tergu.
  • E. Tirico
    Tirico is the surname of American sportscaster Mike Tirico, known for his play-by-play work on major sports broadcasts.
  • 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_69e0b51ad810819098c12392c8e55f6c completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e77ed7732c8190a0e7aec6e7cbcef2 completed April 21, 2026, 1:42 p.m.
NED1 Entity disambiguation (via context triple) batch_6a099ee66f408190962424b053ad54cc completed May 17, 2026, 10:56 a.m.
NEDg Description generation batch_6a099f9aebe4819088658ad23f8f7876 completed May 17, 2026, 10:59 a.m.
NED2 Entity disambiguation (via description) batch_6a09a085b30081909b64de37f2faba35 completed May 17, 2026, 11:03 a.m.
Created at: April 16, 2026, 4:40 p.m.