Triple

T432621
Position Surface form Disambiguated ID Type / Status
Subject Afghanistan E9744 entity
Predicate nationalSport P362 FINISHED
Object buzkashi
Buzkashi is a traditional Central Asian horseback sport in which riders compete to grab and carry a goat or calf carcass to a goal.
 E54478 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: buzkashi | Statement: [Afghanistan, nationalSport, buzkashi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: buzkashi
Context triple: [Afghanistan, nationalSport, buzkashi]
  • A. BO
    BO is the two-letter ISO 3166-1 alpha-2 country code that uniquely identifies Bolivia in international standards and systems.
  • B. BOL
    BOL is the three-letter ISO 3166-1 alpha-3 country code assigned to Bolivia.
  • C. BANZSL
    BANZSL is the family of closely related sign languages used in Britain, Australia, and New Zealand, sharing a common historical origin and many linguistic features.
  • D. KZ
    KZ is the two-letter ISO 3166-1 alpha-2 country code assigned to Kazakhstan for international standardization and identification.
  • E. Bun
    Bun is a modern, high-performance JavaScript runtime and toolkit designed as an alternative to Node.js and Deno, featuring a built-in bundler, test runner, and package manager.
  • 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: buzkashi
Triple: [Afghanistan, nationalSport, buzkashi]
Generated description
Buzkashi is a traditional Central Asian horseback sport in which riders compete to grab and carry a goat or calf carcass to a goal.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: buzkashi
Target entity description: Buzkashi is a traditional Central Asian horseback sport in which riders compete to grab and carry a goat or calf carcass to a goal.
  • A. BO
    BO is the two-letter ISO 3166-1 alpha-2 country code that uniquely identifies Bolivia in international standards and systems.
  • B. BOL
    BOL is the three-letter ISO 3166-1 alpha-3 country code assigned to Bolivia.
  • C. BANZSL
    BANZSL is the family of closely related sign languages used in Britain, Australia, and New Zealand, sharing a common historical origin and many linguistic features.
  • D. KZ
    KZ is the two-letter ISO 3166-1 alpha-2 country code assigned to Kazakhstan for international standardization and identification.
  • E. Bun
    Bun is a modern, high-performance JavaScript runtime and toolkit designed as an alternative to Node.js and Deno, featuring a built-in bundler, test runner, and package manager.
  • 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_69a2e801e1d48190b505d1dd336b52ac completed Feb. 28, 2026, 1:05 p.m.
NER Named-entity recognition batch_69a2eef07e748190b05392778f3de980 completed Feb. 28, 2026, 1:34 p.m.
NED1 Entity disambiguation (via context triple) batch_69a431e395208190ab4d4d1c10c117f7 completed March 1, 2026, 12:32 p.m.
NEDg Description generation batch_69a43257175081909c02f7622fccb6b7 completed March 1, 2026, 12:34 p.m.
NED2 Entity disambiguation (via description) batch_69a432bcb5988190ace76655d26c3428 completed March 1, 2026, 12:36 p.m.
Created at: Feb. 28, 2026, 1:11 p.m.