Triple

T4204823
Position Surface form Disambiguated ID Type / Status
Subject Saigyō E86157 entity
Predicate notableWork P4 FINISHED
Object Sankashū
Sankashū is a renowned anthology of waka poetry by the Japanese poet-monk Saigyō, celebrated for its deeply reflective and nature-focused verse from the late Heian period.
 E526719 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: Sankashū | Statement: [Saigyō, notableWork, Sankashū]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Sankashū
Context triple: [Saigyō, notableWork, Sankashū]
  • A. Takamikura
    Takamikura is the ornate imperial throne used in Kyoto for the enthronement ceremonies of Japanese emperors.
  • B. Shikaoi
    Shikaoi is a rural town in Hokkaido, Japan, known for its natural scenery, agriculture, and access to outdoor activities such as hiking and hot springs.
  • C. Gotemba
    Gotemba is a Japanese city in Shizuoka Prefecture known as a gateway to Mount Fuji and a popular base for outdoor activities and outlet shopping.
  • D. Seishirō
    Seishirō is a Japanese given name commonly used for male individuals.
  • E. Shunpanrō
    Shunpanrō is a historic inn in Shimonoseki, Japan, best known as the site where the Treaty of Shimonoseki ending the First Sino-Japanese War was signed.
  • 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: Sankashū
Triple: [Saigyō, notableWork, Sankashū]
Generated description
Sankashū is a renowned anthology of waka poetry by the Japanese poet-monk Saigyō, celebrated for its deeply reflective and nature-focused verse from the late Heian period.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Sankashū
Target entity description: Sankashū is a renowned anthology of waka poetry by the Japanese poet-monk Saigyō, celebrated for its deeply reflective and nature-focused verse from the late Heian period.
  • A. Takamikura
    Takamikura is the ornate imperial throne used in Kyoto for the enthronement ceremonies of Japanese emperors.
  • B. Shikaoi
    Shikaoi is a rural town in Hokkaido, Japan, known for its natural scenery, agriculture, and access to outdoor activities such as hiking and hot springs.
  • C. Gotemba
    Gotemba is a Japanese city in Shizuoka Prefecture known as a gateway to Mount Fuji and a popular base for outdoor activities and outlet shopping.
  • D. Seishirō
    Seishirō is a Japanese given name commonly used for male individuals.
  • E. Shunpanrō
    Shunpanrō is a historic inn in Shimonoseki, Japan, best known as the site where the Treaty of Shimonoseki ending the First Sino-Japanese War was signed.
  • 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_69aed93b89f48190a31f6d57c760e42f completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69af0382eafc8190946bf45bf28095dd completed March 9, 2026, 5:29 p.m.
NED1 Entity disambiguation (via context triple) batch_69bfc60426248190947e1c58fe4dd1b1 completed March 22, 2026, 10:35 a.m.
NEDg Description generation batch_69bfc68e23b8819089c22cd1ca5fd321 completed March 22, 2026, 10:38 a.m.
NED2 Entity disambiguation (via description) batch_69bfc6de1930819084c599e2af7899b1 completed March 22, 2026, 10:39 a.m.
Created at: March 9, 2026, 3:49 p.m.