Triple

T23376365
Position Surface form Disambiguated ID Type / Status
Subject 神宮 E593615 entity
Predicate isComponentOfName P90387 FINISHED
Object 鹿島神宮
鹿島神宮 is a major Shinto shrine in Kashima, Ibaraki Prefecture, revered as one of Japan’s oldest shrines and the principal center of worship for the deity Takemikazuchi.
 E1584366 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: 鹿島神宮 | Statement: [神宮, isComponentOfName, 鹿島神宮]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: 鹿島神宮
Context triple: [神宮, isComponentOfName, 鹿島神宮]
  • A. 意賀美神社
    意賀美神社は、大阪府枚方市に鎮座し、古くから地域の人々に親しまれている歴史ある神社です。
  • B. 八幡宮
    八幡宮 is a type of Shinto shrine in Japan dedicated to the kami Hachiman, revered as a protector of warriors and the nation.
  • C. 生田神社
    生田神社は、兵庫県神戸市中央区にある古社で、縁結びや安産のご利益で知られる神戸を代表する神社です。
  • D. 愛宕神社
    愛宕神社 is a historic Shinto shrine in Tokyo renowned for its hilltop location on Mount Atago and its steep stone staircase, attracting visitors for both worship and scenic city views.
  • E. 日枝神社
    日枝神社 is a prominent Shinto shrine in Tokyo, Japan, revered as the guardian shrine of the city and known for its Sanno Matsuri festival.
  • 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: 鹿島神宮
Triple: [神宮, isComponentOfName, 鹿島神宮]
Generated description
鹿島神宮 is a major Shinto shrine in Kashima, Ibaraki Prefecture, revered as one of Japan’s oldest shrines and the principal center of worship for the deity Takemikazuchi.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: 鹿島神宮
Target entity description: 鹿島神宮 is a major Shinto shrine in Kashima, Ibaraki Prefecture, revered as one of Japan’s oldest shrines and the principal center of worship for the deity Takemikazuchi.
  • A. 意賀美神社
    意賀美神社は、大阪府枚方市に鎮座し、古くから地域の人々に親しまれている歴史ある神社です。
  • B. 八幡宮
    八幡宮 is a type of Shinto shrine in Japan dedicated to the kami Hachiman, revered as a protector of warriors and the nation.
  • C. 生田神社
    生田神社は、兵庫県神戸市中央区にある古社で、縁結びや安産のご利益で知られる神戸を代表する神社です。
  • D. 愛宕神社
    愛宕神社 is a historic Shinto shrine in Tokyo renowned for its hilltop location on Mount Atago and its steep stone staircase, attracting visitors for both worship and scenic city views.
  • E. 日枝神社
    日枝神社 is a prominent Shinto shrine in Tokyo, Japan, revered as the guardian shrine of the city and known for its Sanno Matsuri festival.
  • 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_69e25d268a50819095f2fd479da8ef3f completed April 17, 2026, 4:17 p.m.
NER Named-entity recognition batch_69f1a3b3cc348190953d0b0ebac9c5dd completed April 29, 2026, 6:22 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0c5de1c1748190994c4a95d0592fef completed May 19, 2026, 12:56 p.m.
NEDg Description generation batch_6a0c62554bbc8190bf8b2302f1e4be01 completed May 19, 2026, 1:15 p.m.
NED2 Entity disambiguation (via description) batch_6a0c62f9fba081908d822630e09d3bee completed May 19, 2026, 1:17 p.m.
Created at: April 17, 2026, 5:33 p.m.