Triple

T10130536
Position Surface form Disambiguated ID Type / Status
Subject Tsurugaoka Hachimangū E226325 entity
Predicate hasTorii P25751 FINISHED
Object Ōtorii
Ōtorii is the large, prominent Shinto shrine gate that serves as a symbolic entrance to Tsurugaoka Hachimangū in Kamakura, Japan.
E845269 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: Ōtorii | Statement: [Tsurugaoka Hachimangū, hasTorii, Ōtorii]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ōtorii
Context triple: [Tsurugaoka Hachimangū, hasTorii, Ōtorii]
  • A. Takanami
    Takanami was a Japanese destroyer of the Imperial Japanese Navy during World War II, notable for being sunk in the Battle of Tassafaronga in 1942.
  • B. Inori
    Inori is a large-scale 1974–1977 composition by Karlheinz Stockhausen that combines orchestra and a soloist performing stylized ritual gestures, exploring the fusion of music and prayer.
  • C. Ōhira
    Ōhira is a Japanese surname most notably associated with Masayoshi Ōhira, a former Prime Minister of Japan.
  • D. Sumio
    Sumio is a Japanese physicist best known for his pioneering discovery and characterization of carbon nanotubes.
  • E. Takaishi
    Takaishi is a city in Osaka Prefecture, Japan, known as a small industrial and residential hub within the Osaka metropolitan 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: Ōtorii
Triple: [Tsurugaoka Hachimangū, hasTorii, Ōtorii]
Generated description
Ōtorii is the large, prominent Shinto shrine gate that serves as a symbolic entrance to Tsurugaoka Hachimangū in Kamakura, Japan.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Ōtorii
Target entity description: Ōtorii is the large, prominent Shinto shrine gate that serves as a symbolic entrance to Tsurugaoka Hachimangū in Kamakura, Japan.
  • A. Takanami
    Takanami was a Japanese destroyer of the Imperial Japanese Navy during World War II, notable for being sunk in the Battle of Tassafaronga in 1942.
  • B. Inori
    Inori is a large-scale 1974–1977 composition by Karlheinz Stockhausen that combines orchestra and a soloist performing stylized ritual gestures, exploring the fusion of music and prayer.
  • C. Ōhira
    Ōhira is a Japanese surname most notably associated with Masayoshi Ōhira, a former Prime Minister of Japan.
  • D. Sumio
    Sumio is a Japanese physicist best known for his pioneering discovery and characterization of carbon nanotubes.
  • E. Takaishi
    Takaishi is a city in Osaka Prefecture, Japan, known as a small industrial and residential hub within the Osaka metropolitan 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_69ca843057b48190a86730167f5d6b98 completed March 30, 2026, 2:09 p.m.
NER Named-entity recognition batch_69cdd33438988190be45878f98695816 completed April 2, 2026, 2:23 a.m.
NED1 Entity disambiguation (via context triple) batch_69d3007765048190992c9a146ab0f1f6 completed April 6, 2026, 12:38 a.m.
NEDg Description generation batch_69d301dd614481909b357f319ba5e876 completed April 6, 2026, 12:44 a.m.
NED2 Entity disambiguation (via description) batch_69d302978e808190a9f5371a2bf4abce completed April 6, 2026, 12:47 a.m.
Created at: March 30, 2026, 9:05 p.m.