Triple

T14930808
Position Surface form Disambiguated ID Type / Status
Subject Temple 47: Yasakaji E372257 entity
Predicate hasRomanizedName P2508 FINISHED
Object Yasakaji
Yasakaji is a Buddhist temple in Japan known as Temple 47 on the Shikoku Pilgrimage.
E1148059 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: Yasakaji | Statement: [Temple 47: Yasakaji, hasRomanizedName, Yasakaji]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Yasakaji
Context triple: [Temple 47: Yasakaji, hasRomanizedName, Yasakaji]
  • A. Akizuki
    Akizuki was a Japanese Akizuki-class destroyer of the Imperial Japanese Navy that served in World War II before being sunk in the Battle off Cape Engaño in 1944.
  • B. Yotsugi
    Yotsugi is a residential neighborhood in Tokyo, Japan, located within Katsushika Ward and known for its local shopping streets and traditional shitamachi atmosphere.
  • C. Katsuragi
    Katsuragi was a late-war Imperial Japanese Navy aircraft carrier that served in the Pacific Theater during World War II.
  • D. Katsuragi
    Katsuragi is a city in Japan known for its location in Nara Prefecture and its historical and cultural ties to the ancient Yamato region.
  • E. Jashugan
    Jashugan is a legendary and fearsome Motorball champion in the manga series "Gunnm" (also known as "Battle Angel Alita"), renowned for his unmatched combat prowess and imposing presence.
  • 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: Yasakaji
Triple: [Temple 47: Yasakaji, hasRomanizedName, Yasakaji]
Generated description
Yasakaji is a Buddhist temple in Japan known as Temple 47 on the Shikoku Pilgrimage.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Yasakaji
Target entity description: Yasakaji is a Buddhist temple in Japan known as Temple 47 on the Shikoku Pilgrimage.
  • A. Akizuki
    Akizuki was a Japanese Akizuki-class destroyer of the Imperial Japanese Navy that served in World War II before being sunk in the Battle off Cape Engaño in 1944.
  • B. Yotsugi
    Yotsugi is a residential neighborhood in Tokyo, Japan, located within Katsushika Ward and known for its local shopping streets and traditional shitamachi atmosphere.
  • C. Katsuragi
    Katsuragi was a late-war Imperial Japanese Navy aircraft carrier that served in the Pacific Theater during World War II.
  • D. Katsuragi
    Katsuragi is a city in Japan known for its location in Nara Prefecture and its historical and cultural ties to the ancient Yamato region.
  • E. Jashugan
    Jashugan is a legendary and fearsome Motorball champion in the manga series "Gunnm" (also known as "Battle Angel Alita"), renowned for his unmatched combat prowess and imposing presence.
  • 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_69d85cc9da0c81908d583ca3f63a3908 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69ded64550dc8190ba44120df00ba498 completed April 15, 2026, 12:05 a.m.
NED1 Entity disambiguation (via context triple) batch_69feef603b788190ad747d73af2363d4 completed May 9, 2026, 8:25 a.m.
NEDg Description generation batch_69fef0f34c84819089e59789eeb12074 completed May 9, 2026, 8:31 a.m.
NED2 Entity disambiguation (via description) batch_69fef23174a88190bdbe89a7ded4c782 completed May 9, 2026, 8:37 a.m.
Created at: April 10, 2026, 2:36 a.m.