Triple

T14839500
Position Surface form Disambiguated ID Type / Status
Subject Baghlan Province E348921 entity
Predicate hasCity P316 FINISHED
Object Doshi
Doshi is a town in northern Afghanistan that serves as a local administrative and commercial center in Baghlan Province.
 E1121855 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: Doshi | Statement: [Baghlan Province, hasCity, Doshi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Doshi
Context triple: [Baghlan Province, hasCity, Doshi]
  • A. Doshi
    Doshi is an Indian surname notably associated with the acclaimed architect and Pritzker Prize laureate Balkrishna Doshi.
  • B. Daisi
    Daisi is a Georgian opera by composer Zakharia Paliashvili, renowned as one of the classics of Georgian national opera repertoire.
  • C. Toshi
    Toshi is a Japanese given name commonly used for both males and females, often as a short form of longer names such as Toshiro or Toshiko.
  • D. Dinsho
    Dinsho is a small town in Ethiopia’s Bale Mountains region, known as a gateway to Bale Mountains National Park and a base for trekking and wildlife viewing.
  • E. Dori
    Dori is a dwarf from J.R.R. Tolkien's "The Hobbit," known as one of Thorin Oakenshield's companions on the quest to reclaim Erebor.
  • 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: Doshi
Triple: [Baghlan Province, hasCity, Doshi]
Generated description
Doshi is a town in northern Afghanistan that serves as a local administrative and commercial center in Baghlan Province.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Doshi
Target entity description: Doshi is a town in northern Afghanistan that serves as a local administrative and commercial center in Baghlan Province.
  • A. Doshi
    Doshi is an Indian surname notably associated with the acclaimed architect and Pritzker Prize laureate Balkrishna Doshi.
  • B. Daisi
    Daisi is a Georgian opera by composer Zakharia Paliashvili, renowned as one of the classics of Georgian national opera repertoire.
  • C. Toshi
    Toshi is a Japanese given name commonly used for both males and females, often as a short form of longer names such as Toshiro or Toshiko.
  • D. Dinsho
    Dinsho is a small town in Ethiopia’s Bale Mountains region, known as a gateway to Bale Mountains National Park and a base for trekking and wildlife viewing.
  • E. Dori
    Dori is a dwarf from J.R.R. Tolkien's "The Hobbit," known as one of Thorin Oakenshield's companions on the quest to reclaim Erebor.
  • 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_69d822ec69008190a9232caa68836872 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69ded28e40f08190b309d8ac6404d2fc completed April 14, 2026, 11:49 p.m.
NED1 Entity disambiguation (via context triple) batch_69fe38a813b881908a71350073c8fc5c completed May 8, 2026, 7:25 p.m.
NEDg Description generation batch_69fe5096b15481908f7794f9da78141a completed May 8, 2026, 9:07 p.m.
NED2 Entity disambiguation (via description) batch_69fe510d4164819080c4000af3e39bf8 completed May 8, 2026, 9:09 p.m.
Created at: April 10, 2026, 1:52 a.m.