Triple

T22780186
Position Surface form Disambiguated ID Type / Status
Subject Wado-ryu E563814 entity
Predicate hasKata P149698 FINISHED
Object Jion
Jion is a traditional karate kata, shared across several styles, known for its balanced combination of powerful basic techniques and straightforward, practical applications.
E1553756 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: Jion | Statement: [Wado-ryu, hasKata, Jion]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jion
Context triple: [Wado-ryu, hasKata, Jion]
  • A. Jino
    Jino are an officially recognized ethnic minority group in China, primarily living in Yunnan Province and known for their distinct language and traditional culture.
  • B. Junshi
    Junshi was the courtesy name of Sima Guang, a prominent Song dynasty historian and statesman best known for compiling the comprehensive chronicle "Zizhi Tongjian."
  • C. Jinki
    Jinki was a Japanese era name (nengō) of the Nara period, used during the reign of Empress Genshō.
  • D. Oedo
    Oedo is a small, scenic South Korean island famous for its botanical garden and dramatic coastal landscapes, located off the coast of Geoje.
  • E. Jurame
    "Jurame" is a popular romantic Latin song, often performed as a bolero, that has been interpreted by numerous artists across the Spanish-speaking world.
  • 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: Jion
Triple: [Wado-ryu, hasKata, Jion]
Generated description
Jion is a traditional karate kata, shared across several styles, known for its balanced combination of powerful basic techniques and straightforward, practical applications.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Jion
Target entity description: Jion is a traditional karate kata, shared across several styles, known for its balanced combination of powerful basic techniques and straightforward, practical applications.
  • A. Jino
    Jino are an officially recognized ethnic minority group in China, primarily living in Yunnan Province and known for their distinct language and traditional culture.
  • B. Junshi
    Junshi was the courtesy name of Sima Guang, a prominent Song dynasty historian and statesman best known for compiling the comprehensive chronicle "Zizhi Tongjian."
  • C. Jinki
    Jinki was a Japanese era name (nengō) of the Nara period, used during the reign of Empress Genshō.
  • D. Oedo
    Oedo is a small, scenic South Korean island famous for its botanical garden and dramatic coastal landscapes, located off the coast of Geoje.
  • E. Jurame
    "Jurame" is a popular romantic Latin song, often performed as a bolero, that has been interpreted by numerous artists across the Spanish-speaking world.
  • 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_69e24554497c819080b996e071de27c2 completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f17c2cab0881908df1d0629b43d350 completed April 29, 2026, 3:34 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0b98291e208190be3e92b57cf2fccd completed May 18, 2026, 10:52 p.m.
NEDg Description generation batch_6a0b992ef5d0819081957a9633260400 completed May 18, 2026, 10:56 p.m.
NED2 Entity disambiguation (via description) batch_6a0b9a1129c8819084163353accc7e14 completed May 18, 2026, 11 p.m.
Created at: April 17, 2026, 3:28 p.m.