Triple

T13852358
Position Surface form Disambiguated ID Type / Status
Subject Rubirizi District E332975 entity
Predicate hasMajorTown P316 FINISHED
Object Kashenyi
Kashenyi is a town in western Uganda that serves as one of the main urban centers in Rubirizi District.
 E1067451 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: Kashenyi | Statement: [Rubirizi District, hasMajorTown, Kashenyi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Kashenyi
Context triple: [Rubirizi District, hasMajorTown, Kashenyi]
  • A. Kashshaya
    Kashshaya was a Neo-Babylonian royal woman known primarily as the wife of King Amel-Marduk.
  • B. Kabany
    Kabany is a rural locality in present-day Ukraine, historically part of the Russian Empire and known as the birthplace of Soviet politician Lazar Kaganovich.
  • C. Kopaska
    Kopaska is the Indonesian Navy’s elite frogman and special operations unit, specializing in underwater demolition, maritime sabotage, and counter-terrorism missions.
  • D. Kutiyana
    Kutiyana is a town in the Porbandar district of Gujarat, India, known historically as a local trading and administrative center.
  • E. Kasplya
    Kasplya is a river in Eastern Europe that serves as a tributary of the Western Dvina (Daugava) River.
  • 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: Kashenyi
Triple: [Rubirizi District, hasMajorTown, Kashenyi]
Generated description
Kashenyi is a town in western Uganda that serves as one of the main urban centers in Rubirizi District.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Kashenyi
Target entity description: Kashenyi is a town in western Uganda that serves as one of the main urban centers in Rubirizi District.
  • A. Kashshaya
    Kashshaya was a Neo-Babylonian royal woman known primarily as the wife of King Amel-Marduk.
  • B. Kabany
    Kabany is a rural locality in present-day Ukraine, historically part of the Russian Empire and known as the birthplace of Soviet politician Lazar Kaganovich.
  • C. Kopaska
    Kopaska is the Indonesian Navy’s elite frogman and special operations unit, specializing in underwater demolition, maritime sabotage, and counter-terrorism missions.
  • D. Kutiyana
    Kutiyana is a town in the Porbandar district of Gujarat, India, known historically as a local trading and administrative center.
  • E. Kasplya
    Kasplya is a river in Eastern Europe that serves as a tributary of the Western Dvina (Daugava) River.
  • 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_69d81c5ba13c8190839315f54768acfd completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de02da9460819093a3ec5a3c62ea81 completed April 14, 2026, 9:03 a.m.
NED1 Entity disambiguation (via context triple) batch_69f7c70a59e8819090b750699993a107 completed May 3, 2026, 10:07 p.m.
NEDg Description generation batch_69f7c7e1247481908073c1e282c3619f completed May 3, 2026, 10:10 p.m.
NED2 Entity disambiguation (via description) batch_69f7c8f2b5588190b6143d676eb648a0 completed May 3, 2026, 10:15 p.m.
Created at: April 9, 2026, 10:14 p.m.