Triple

T16206794
Position Surface form Disambiguated ID Type / Status
Subject Emperor Kōnin E393348 entity
Predicate personalName P24312 FINISHED
Object Shirakabe
Shirakabe was the personal name of Emperor Kōnin, a Nara-period Japanese ruler who reigned in the late 8th century.
E1201308 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: Shirakabe | Statement: [Emperor Kōnin, personalName, Shirakabe]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Shirakabe
Context triple: [Emperor Kōnin, personalName, Shirakabe]
  • A. Kamitsumaki
    Kamitsumaki is the first volume of the ancient Japanese chronicle Kojiki, focusing on Shinto creation myths and the age of the gods.
  • B. Higashiizu
    Higashiizu is a coastal town in Shizuoka Prefecture, Japan, known for its hot springs, scenic Pacific shoreline, and views of the Izu Islands.
  • C. Shizunai
    Shizunai was a former town in Hokkaido, Japan, known for its horse-breeding traditions and later incorporated into the town of Shinhidaka.
  • D. Kitasenju
    Kitasenju is a major commercial and transportation hub in Adachi, Tokyo, known for its busy train station, shopping complexes, and urban downtown atmosphere.
  • E. Yokoze
    Yokoze is a small town in Saitama Prefecture, Japan, known for its rural scenery and proximity to the Chichibu mountain area.
  • 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: Shirakabe
Triple: [Emperor Kōnin, personalName, Shirakabe]
Generated description
Shirakabe was the personal name of Emperor Kōnin, a Nara-period Japanese ruler who reigned in the late 8th century.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Shirakabe
Target entity description: Shirakabe was the personal name of Emperor Kōnin, a Nara-period Japanese ruler who reigned in the late 8th century.
  • A. Kamitsumaki
    Kamitsumaki is the first volume of the ancient Japanese chronicle Kojiki, focusing on Shinto creation myths and the age of the gods.
  • B. Higashiizu
    Higashiizu is a coastal town in Shizuoka Prefecture, Japan, known for its hot springs, scenic Pacific shoreline, and views of the Izu Islands.
  • C. Shizunai
    Shizunai was a former town in Hokkaido, Japan, known for its horse-breeding traditions and later incorporated into the town of Shinhidaka.
  • D. Kitasenju
    Kitasenju is a major commercial and transportation hub in Adachi, Tokyo, known for its busy train station, shopping complexes, and urban downtown atmosphere.
  • E. Yokoze
    Yokoze is a small town in Saitama Prefecture, Japan, known for its rural scenery and proximity to the Chichibu mountain area.
  • 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_69d87f1f5bd08190bd01cac0d5b9d2ef completed April 10, 2026, 4:39 a.m.
NER Named-entity recognition batch_69e227101a3c819095ef40e50bf66433 completed April 17, 2026, 12:26 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00078fa2ac8190a0a2cf38bc41498d completed May 10, 2026, 4:20 a.m.
NEDg Description generation batch_6a000900bfbc8190b21eb513838759a9 completed May 10, 2026, 4:26 a.m.
NED2 Entity disambiguation (via description) batch_6a000a0fc93c819088d9233aaa5e2017 completed May 10, 2026, 4:31 a.m.
Created at: April 10, 2026, 5:03 a.m.