Triple

T3578434
Position Surface form Disambiguated ID Type / Status
Subject Koshi River E75742 entity
Predicate majorTributary P415 FINISHED
Object Sun Koshi
Sun Koshi is a significant Himalayan river in Nepal known for its long, challenging whitewater rafting routes and contribution to the Koshi river system.
 E370117 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: Sun Koshi | Statement: [Koshi River, majorTributary, Sun Koshi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Sun Koshi
Context triple: [Koshi River, majorTributary, Sun Koshi]
  • A. Yasu
    Yasu is a Japanese city located in Shiga Prefecture, known for its blend of residential areas, local industry, and proximity to Lake Biwa.
  • B. Takaishi
    Takaishi is a city in Osaka Prefecture, Japan, known as a small industrial and residential hub within the Osaka metropolitan area.
  • C. Shimotsuki
    Shimotsuki was a Japanese destroyer of the Imperial Japanese Navy that served in World War II before being sunk in late 1944.
  • D. Kashin
    Kashin is a historic town in western Russia known for its medieval heritage and location along the Kashinka River.
  • E. Haramosh Shina
    Haramosh Shina is a regional dialect of the Shina language spoken in the Haramosh area of northern Pakistan.
  • 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: Sun Koshi
Triple: [Koshi River, majorTributary, Sun Koshi]
Generated description
Sun Koshi is a significant Himalayan river in Nepal known for its long, challenging whitewater rafting routes and contribution to the Koshi river system.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Sun Koshi
Target entity description: Sun Koshi is a significant Himalayan river in Nepal known for its long, challenging whitewater rafting routes and contribution to the Koshi river system.
  • A. Yasu
    Yasu is a Japanese city located in Shiga Prefecture, known for its blend of residential areas, local industry, and proximity to Lake Biwa.
  • B. Takaishi
    Takaishi is a city in Osaka Prefecture, Japan, known as a small industrial and residential hub within the Osaka metropolitan area.
  • C. Shimotsuki
    Shimotsuki was a Japanese destroyer of the Imperial Japanese Navy that served in World War II before being sunk in late 1944.
  • D. Kashin
    Kashin is a historic town in western Russia known for its medieval heritage and location along the Kashinka River.
  • E. Haramosh Shina
    Haramosh Shina is a regional dialect of the Shina language spoken in the Haramosh area of northern Pakistan.
  • 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_69ad85d5e3008190bdfe0bacdd1f5a1b completed March 8, 2026, 2:21 p.m.
NER Named-entity recognition batch_69adc0defe14819095a337a840e33300 completed March 8, 2026, 6:33 p.m.
NED1 Entity disambiguation (via context triple) batch_69b3bbc6bc948190a517639f5d79c0a3 completed March 13, 2026, 7:24 a.m.
NEDg Description generation batch_69b3bc93f93c8190a23301340b08d76b completed March 13, 2026, 7:28 a.m.
NED2 Entity disambiguation (via description) batch_69b3f8033cd481909bc0e24fd9d86831 completed March 13, 2026, 11:41 a.m.
Created at: March 8, 2026, 3:21 p.m.