Triple

T13528169
Position Surface form Disambiguated ID Type / Status
Subject Saga Castle E323064 entity
Predicate nativeName P15 FINISHED
Object 佐賀城
佐賀城は、佐賀県佐賀市に位置し、江戸時代に肥前佐賀藩の政治・軍事の中心として機能した日本の平城です。
E1044962 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: 佐賀城 | Statement: [Saga Castle, nativeName, 佐賀城]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: 佐賀城
Context triple: [Saga Castle, nativeName, 佐賀城]
  • A. Takamatsu Castle
    Takamatsu Castle is a historic Japanese seaside fortress in Kagawa Prefecture, noted for its rare seawater moats and Edo-period architecture.
  • B. 久保田城跡
    久保田城跡は、秋田藩佐竹氏の居城であった久保田城の遺構が残る秋田市の歴史的史跡です。
  • C. Karatsu Castle
    Karatsu Castle is a historic Japanese hilltop fortress in Karatsu, Saga Prefecture, known for its scenic seaside views and Edo-period architecture.
  • D. Okazaki Castle
    Okazaki Castle is a historic Japanese fortress in Aichi Prefecture, best known as the birthplace of shogun Tokugawa Ieyasu and a key stronghold in the Sengoku and early Edo periods.
  • E. Matsue Castle
    Matsue Castle is a well-preserved early 17th-century Japanese feudal castle in Shimane Prefecture, renowned as one of the few remaining original wooden castles in Japan.
  • 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: 佐賀城
Triple: [Saga Castle, nativeName, 佐賀城]
Generated description
佐賀城は、佐賀県佐賀市に位置し、江戸時代に肥前佐賀藩の政治・軍事の中心として機能した日本の平城です。
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: 佐賀城
Target entity description: 佐賀城は、佐賀県佐賀市に位置し、江戸時代に肥前佐賀藩の政治・軍事の中心として機能した日本の平城です。
  • A. Takamatsu Castle
    Takamatsu Castle is a historic Japanese seaside fortress in Kagawa Prefecture, noted for its rare seawater moats and Edo-period architecture.
  • B. 久保田城跡
    久保田城跡は、秋田藩佐竹氏の居城であった久保田城の遺構が残る秋田市の歴史的史跡です。
  • C. Karatsu Castle
    Karatsu Castle is a historic Japanese hilltop fortress in Karatsu, Saga Prefecture, known for its scenic seaside views and Edo-period architecture.
  • D. Okazaki Castle
    Okazaki Castle is a historic Japanese fortress in Aichi Prefecture, best known as the birthplace of shogun Tokugawa Ieyasu and a key stronghold in the Sengoku and early Edo periods.
  • E. Matsue Castle
    Matsue Castle is a well-preserved early 17th-century Japanese feudal castle in Shimane Prefecture, renowned as one of the few remaining original wooden castles in Japan.
  • 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_69d80766a21881909f21a1b7421d3b8a completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69dbafb8e0cc8190b47f6aeb8ced470e completed April 12, 2026, 2:44 p.m.
NED1 Entity disambiguation (via context triple) batch_69f7549dda6481908e9305690488b1af completed May 3, 2026, 1:58 p.m.
NEDg Description generation batch_69f7555173d08190be887e81c148192e completed May 3, 2026, 2:01 p.m.
NED2 Entity disambiguation (via description) batch_69f756773b9c81908250ae7ffc2d8d99 completed May 3, 2026, 2:06 p.m.
Created at: April 9, 2026, 9:44 p.m.