Triple

T11934296
Position Surface form Disambiguated ID Type / Status
Subject 文京区 E283998 entity
Predicate hasCulturalFacility P2412 FINISHED
Object 講道館
講道館は、嘉納治五郎が創設した日本の柔道の総本山として知られる道場・教育機関です。
E954809 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: 講道館 | Statement: [文京区, hasCulturalFacility, 講道館]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: 講道館
Context triple: [文京区, hasCulturalFacility, 講道館]
  • A. Yushima Seidō
    Yushima Seidō is a historic Confucian temple and former educational center in Tokyo, Japan, known as a key site for Confucian learning during the Edo period.
  • B. Jōgyō-dō
    Jōgyō-dō is a significant hall within Enryaku-ji on Mount Hiei, associated with traditional Tendai Buddhist devotional practices and monastic training.
  • C. Shinnyo-en
    Shinnyo-en is a Japanese Buddhist new religious movement known for its lay-centered practice, focus on meditation and spiritual training, and emphasis on universal enlightenment and peace.
  • D. Sanjūsangen-dō
    Sanjūsangen-dō is a historic Buddhist temple hall in Kyoto, Japan, renowned for its 1,001 statues of Kannon and its exceptionally long wooden structure.
  • E. Shōka Sonjuku academy
    Shōka Sonjuku academy was a small but highly influential private school in late Edo-period Japan, led by Yoshida Shōin and known for educating many key figures who later drove the Meiji Restoration.
  • 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: 講道館
Triple: [文京区, hasCulturalFacility, 講道館]
Generated description
講道館は、嘉納治五郎が創設した日本の柔道の総本山として知られる道場・教育機関です。
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: 講道館
Target entity description: 講道館は、嘉納治五郎が創設した日本の柔道の総本山として知られる道場・教育機関です。
  • A. Yushima Seidō
    Yushima Seidō is a historic Confucian temple and former educational center in Tokyo, Japan, known as a key site for Confucian learning during the Edo period.
  • B. Jōgyō-dō
    Jōgyō-dō is a significant hall within Enryaku-ji on Mount Hiei, associated with traditional Tendai Buddhist devotional practices and monastic training.
  • C. Shinnyo-en
    Shinnyo-en is a Japanese Buddhist new religious movement known for its lay-centered practice, focus on meditation and spiritual training, and emphasis on universal enlightenment and peace.
  • D. Sanjūsangen-dō
    Sanjūsangen-dō is a historic Buddhist temple hall in Kyoto, Japan, renowned for its 1,001 statues of Kannon and its exceptionally long wooden structure.
  • E. Shōka Sonjuku academy
    Shōka Sonjuku academy was a small but highly influential private school in late Edo-period Japan, led by Yoshida Shōin and known for educating many key figures who later drove the Meiji Restoration.
  • 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_69d6ab2ce9c48190b5d39511b524f666 completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d90306fcf48190a963d2d1932288d1 completed April 10, 2026, 2:02 p.m.
NED1 Entity disambiguation (via context triple) batch_69f4407cc2388190b0f849fbeed89ab7 completed May 1, 2026, 5:56 a.m.
NEDg Description generation batch_69f448fc874081908fe05f9d8aff11a3 completed May 1, 2026, 6:32 a.m.
NED2 Entity disambiguation (via description) batch_69f44afdc7b08190bdf47cfcb94c34c8 completed May 1, 2026, 6:41 a.m.
Created at: April 8, 2026, 9:45 p.m.