Triple

T16518873
Position Surface form Disambiguated ID Type / Status
Subject Hanshin Racecourse E401261 entity
Predicate hostsRace P64218 FINISHED
Object Sakura Sho
Sakura Sho is a Japanese horse racing event held at Hanshin Racecourse, known as a key race in the country's thoroughbred racing calendar.
 E1218519 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: Sakura Sho | Statement: [Hanshin Racecourse, hostsRace, Sakura Sho]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Sakura Sho
Context triple: [Hanshin Racecourse, hostsRace, Sakura Sho]
  • A. Sakura
    Sakura is a Japanese high-speed Shinkansen train service that operates mainly on the Sanyo and Kyushu Shinkansen lines.
  • B. Someiyoshino
    Someiyoshino is Japan’s most widely planted and iconic cherry blossom cultivar, known for its pale pink flowers that bloom in dramatic unison each spring.
  • C. Seika
    Seika is a town in Kyoto Prefecture, Japan, known for its residential communities and proximity to the Kansai Science City area.
  • D. Kyoko Sakura
    Kyoko Sakura is a spear-wielding, food-loving magical girl known for her brash attitude and tragic past in the anime series Puella Magi Madoka Magica.
  • E. Itsuka
    Itsuka is a novel by Joy Kogawa that continues the story of Japanese Canadians grappling with the legacy of wartime internment and the struggle for redress.
  • 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: Sakura Sho
Triple: [Hanshin Racecourse, hostsRace, Sakura Sho]
Generated description
Sakura Sho is a Japanese horse racing event held at Hanshin Racecourse, known as a key race in the country's thoroughbred racing calendar.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Sakura Sho
Target entity description: Sakura Sho is a Japanese horse racing event held at Hanshin Racecourse, known as a key race in the country's thoroughbred racing calendar.
  • A. Sakura
    Sakura is a Japanese high-speed Shinkansen train service that operates mainly on the Sanyo and Kyushu Shinkansen lines.
  • B. Someiyoshino
    Someiyoshino is Japan’s most widely planted and iconic cherry blossom cultivar, known for its pale pink flowers that bloom in dramatic unison each spring.
  • C. Seika
    Seika is a town in Kyoto Prefecture, Japan, known for its residential communities and proximity to the Kansai Science City area.
  • D. Kyoko Sakura
    Kyoko Sakura is a spear-wielding, food-loving magical girl known for her brash attitude and tragic past in the anime series Puella Magi Madoka Magica.
  • E. Itsuka
    Itsuka is a novel by Joy Kogawa that continues the story of Japanese Canadians grappling with the legacy of wartime internment and the struggle for redress.
  • 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_69d883838abc8190bc79cb2d41733ce2 completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e32e7ec45c8190b5e2c4a5f707e332 completed April 18, 2026, 7:10 a.m.
NED1 Entity disambiguation (via context triple) batch_6a006086c0a881908976103f8a144f69 completed May 10, 2026, 10:40 a.m.
NEDg Description generation batch_6a006133a9148190af5bc0cec8ad6695 completed May 10, 2026, 10:42 a.m.
NED2 Entity disambiguation (via description) batch_6a0061c85d5481909628c2fddbcf0d54 completed May 10, 2026, 10:45 a.m.
Created at: April 10, 2026, 5:14 a.m.