Triple

T1351923
Position Surface form Disambiguated ID Type / Status
Subject Kosi E28900 entity
Predicate hasTributary P415 FINISHED
Object Sun Kosi
The Sun Kosi is a major Himalayan river in Nepal, renowned for its long white-water rafting expeditions and as a key tributary of the Kosi river system.
E155129 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 Kosi | Statement: [Kosi, hasTributary, Sun Kosi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sun Kosi
Context triple: [Kosi, hasTributary, Sun Kosi]
  • A. Mandla
    Mandla is a town and administrative district headquarters in the central Indian state of Madhya Pradesh, known for its proximity to the Narmada River and nearby wildlife and forested areas.
  • B. Thabana Ntlenyana
    Thabana Ntlenyana is the highest mountain in southern Africa, located in the Drakensberg range within Lesotho.
  • C. Bongi
    Bongi is a neighborhood located in the city of Recife, in northeastern Brazil.
  • D. Madikizela
    Madikizela is the maiden surname of South African anti-apartheid activist and politician Winnie Madikizela-Mandela.
  • E. Nomukhan
    Nomukhan was a Mongol prince of the 13th century who played a role in the politics and military affairs of the early Yuan dynasty under his father Kublai Khan.
  • 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 Kosi
Triple: [Kosi, hasTributary, Sun Kosi]
Generated description
The Sun Kosi is a major Himalayan river in Nepal, renowned for its long white-water rafting expeditions and as a key tributary of the Kosi river system.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Sun Kosi
Target entity description: The Sun Kosi is a major Himalayan river in Nepal, renowned for its long white-water rafting expeditions and as a key tributary of the Kosi river system.
  • A. Mandla
    Mandla is a town and administrative district headquarters in the central Indian state of Madhya Pradesh, known for its proximity to the Narmada River and nearby wildlife and forested areas.
  • B. Thabana Ntlenyana
    Thabana Ntlenyana is the highest mountain in southern Africa, located in the Drakensberg range within Lesotho.
  • C. Bongi
    Bongi is a neighborhood located in the city of Recife, in northeastern Brazil.
  • D. Madikizela
    Madikizela is the maiden surname of South African anti-apartheid activist and politician Winnie Madikizela-Mandela.
  • E. Nomukhan
    Nomukhan was a Mongol prince of the 13th century who played a role in the politics and military affairs of the early Yuan dynasty under his father Kublai Khan.
  • 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_69a498571d248190a0ac9eb02d97097f completed March 1, 2026, 7:49 p.m.
NER Named-entity recognition batch_69a4c26b1b4881908ae4b1b2c9b268a0 completed March 1, 2026, 10:49 p.m.
NED1 Entity disambiguation (via context triple) batch_69acce6a1dd48190b17ac5a7cf3ab933 completed March 8, 2026, 1:18 a.m.
NEDg Description generation batch_69acceac84748190bbf9dd9c9ba5561f completed March 8, 2026, 1:19 a.m.
NED2 Entity disambiguation (via description) batch_69accf1778b081908936977cd9317774 completed March 8, 2026, 1:21 a.m.
Created at: March 1, 2026, 7:56 p.m.