Triple

T5190395
Position Surface form Disambiguated ID Type / Status
Subject Schweizerische Nordostbahn E117137 entity
Predicate servedCity P3936 FINISHED
Object Romanshorn
Romanshorn is a Swiss town on the southern shore of Lake Constance, known as an important regional transport hub and ferry port.
 E524736 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: Romanshorn | Statement: [Schweizerische Nordostbahn, servedCity, Romanshorn]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Romanshorn
Context triple: [Schweizerische Nordostbahn, servedCity, Romanshorn]
  • A. Grenchen
    Grenchen is a Swiss town in the canton of Solothurn known for its watchmaking industry and location at the foot of the Jura Mountains.
  • B. Landquart
    Landquart is a river in eastern Switzerland that flows through the canton of Graubünden before joining the Alpine Rhine.
  • C. Schaffhausen
    Schaffhausen is a historic town and capital of the canton of the same name in northern Switzerland, known for its well-preserved medieval old town and proximity to the Rhine Falls.
  • D. Adliswil
    Adliswil is a municipality in the canton of Zurich, Switzerland, situated in the Sihl Valley just south of the city of Zurich.
  • E. Pratteln
    Pratteln is a municipality in northern Switzerland that serves as a major residential and industrial center in the canton of Basel-Landschaft.
  • 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: Romanshorn
Triple: [Schweizerische Nordostbahn, servedCity, Romanshorn]
Generated description
Romanshorn is a Swiss town on the southern shore of Lake Constance, known as an important regional transport hub and ferry port.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Romanshorn
Target entity description: Romanshorn is a Swiss town on the southern shore of Lake Constance, known as an important regional transport hub and ferry port.
  • A. Grenchen
    Grenchen is a Swiss town in the canton of Solothurn known for its watchmaking industry and location at the foot of the Jura Mountains.
  • B. Landquart
    Landquart is a river in eastern Switzerland that flows through the canton of Graubünden before joining the Alpine Rhine.
  • C. Schaffhausen
    Schaffhausen is a historic town and capital of the canton of the same name in northern Switzerland, known for its well-preserved medieval old town and proximity to the Rhine Falls.
  • D. Adliswil
    Adliswil is a municipality in the canton of Zurich, Switzerland, situated in the Sihl Valley just south of the city of Zurich.
  • E. Pratteln
    Pratteln is a municipality in northern Switzerland that serves as a major residential and industrial center in the canton of Basel-Landschaft.
  • 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_69bd44620ff48190bcac01782107a397 completed March 20, 2026, 12:58 p.m.
NER Named-entity recognition batch_69bd79ebbfd081909a19b903c227fc1f completed March 20, 2026, 4:46 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf77a987ec8190bda4df37468d9918 completed March 22, 2026, 5:01 a.m.
NEDg Description generation batch_69bf7b6b45548190b6766c4625aa8857 completed March 22, 2026, 5:17 a.m.
NED2 Entity disambiguation (via description) batch_69bf7bb6925c81908f8dbc7d18031dc0 completed March 22, 2026, 5:18 a.m.
Created at: March 20, 2026, 1:46 p.m.