Triple

T20718628
Position Surface form Disambiguated ID Type / Status
Subject Linth River E509246 entity
Predicate hasTributary P415 FINISHED
Object Sernf
Sernf is a river in the canton of Glarus in eastern Switzerland that flows through the Sernftal valley before joining the Linth.
E1447664 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: Sernf | Statement: [Linth River, hasTributary, Sernf]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sernf
Context triple: [Linth River, hasTributary, Sernf]
  • A. Sennfeld
    Sennfeld is a municipality in the Schweinfurt district of Bavaria, Germany, known for its traditional Franconian character and proximity to the city of Schweinfurt.
  • B. Zernien
    Zernien is a municipality in Lower Saxony, Germany, situated within the collective municipality (Samtgemeinde) of Elbtalaue.
  • C. Schnelsen
    Schnelsen is a residential district in the northwestern part of Hamburg, Germany, known for its suburban character and proximity to major transport routes.
  • D. Serdi
    The Serdi were an ancient Thracian tribe that inhabited the region around present-day Sofia, Bulgaria, giving their name to the Roman city of Serdica.
  • E. Serting
    Serting is a state constituency in Malaysia that is represented in the Negeri Sembilan State Legislative Assembly.
  • 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: Sernf
Triple: [Linth River, hasTributary, Sernf]
Generated description
Sernf is a river in the canton of Glarus in eastern Switzerland that flows through the Sernftal valley before joining the Linth.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Sernf
Target entity description: Sernf is a river in the canton of Glarus in eastern Switzerland that flows through the Sernftal valley before joining the Linth.
  • A. Sennfeld
    Sennfeld is a municipality in the Schweinfurt district of Bavaria, Germany, known for its traditional Franconian character and proximity to the city of Schweinfurt.
  • B. Zernien
    Zernien is a municipality in Lower Saxony, Germany, situated within the collective municipality (Samtgemeinde) of Elbtalaue.
  • C. Schnelsen
    Schnelsen is a residential district in the northwestern part of Hamburg, Germany, known for its suburban character and proximity to major transport routes.
  • D. Serdi
    The Serdi were an ancient Thracian tribe that inhabited the region around present-day Sofia, Bulgaria, giving their name to the Roman city of Serdica.
  • E. Serting
    Serting is a state constituency in Malaysia that is represented in the Negeri Sembilan State Legislative Assembly.
  • 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_69e0b4c4cc648190b45fda6e2b20af56 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c1d39bec8190b3642b0d6d833375 completed April 21, 2026, 12:16 a.m.
NED1 Entity disambiguation (via context triple) batch_6a08e0552fe88190aa5557fa83b7ed40 completed May 16, 2026, 9:23 p.m.
NEDg Description generation batch_6a08e4808ac881908d527d462833ba84 completed May 16, 2026, 9:41 p.m.
NED2 Entity disambiguation (via description) batch_6a08e4eccb0881908e536964d86650d1 completed May 16, 2026, 9:43 p.m.
Created at: April 16, 2026, 12:25 p.m.