Triple

T5905107
Position Surface form Disambiguated ID Type / Status
Subject 皇居 E131323 entity
Predicate 構成要素 P14960 FINISHED
Object 長和殿
長和殿は、日本の皇居内に位置し、公式行事や儀式などに用いられる主要な宮殿建物の一つである。
E554742 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: 長和殿 | Statement: [皇居, 構成要素, 長和殿]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: 長和殿
Context triple: [皇居, 構成要素, 長和殿]
  • A. 敬宮
    敬宮 is the courtesy name of Princess Aiko, the only child of Emperor Naruhito and Empress Masako of Japan.
  • B. 中和殿
    中和殿 is a ceremonial hall within Beijing’s Forbidden City, historically used by Chinese emperors to rest and prepare before major state rituals.
  • C. 交泰殿
    交泰殿 is a historic hall within Beijing’s Forbidden City, traditionally used for important imperial ceremonies and symbolizing the harmony of heaven and earth in Chinese imperial architecture.
  • D. 仁寿殿
    仁寿殿 is a historic palace hall in Beijing’s Forbidden City, notable as one of the imperial residential and ceremonial buildings of the Ming and Qing dynasties.
  • E. 保和殿
    保和殿 is one of the principal ceremonial halls within Beijing’s Forbidden City, historically used for imperial banquets and important state rituals.
  • 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: 長和殿
Triple: [皇居, 構成要素, 長和殿]
Generated description
長和殿は、日本の皇居内に位置し、公式行事や儀式などに用いられる主要な宮殿建物の一つである。
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: 長和殿
Target entity description: 長和殿は、日本の皇居内に位置し、公式行事や儀式などに用いられる主要な宮殿建物の一つである。
  • A. 敬宮
    敬宮 is the courtesy name of Princess Aiko, the only child of Emperor Naruhito and Empress Masako of Japan.
  • B. 中和殿
    中和殿 is a ceremonial hall within Beijing’s Forbidden City, historically used by Chinese emperors to rest and prepare before major state rituals.
  • C. 交泰殿
    交泰殿 is a historic hall within Beijing’s Forbidden City, traditionally used for important imperial ceremonies and symbolizing the harmony of heaven and earth in Chinese imperial architecture.
  • D. 仁寿殿
    仁寿殿 is a historic palace hall in Beijing’s Forbidden City, notable as one of the imperial residential and ceremonial buildings of the Ming and Qing dynasties.
  • E. 保和殿
    保和殿 is one of the principal ceremonial halls within Beijing’s Forbidden City, historically used for imperial banquets and important state rituals.
  • 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_69c0085864a88190a569c05ff7d65f29 completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c049fdb3e08190a72337ab4f48bc8e completed March 22, 2026, 7:58 p.m.
NED1 Entity disambiguation (via context triple) batch_69c0b16ba6c881908e9a909bf86ea92d completed March 23, 2026, 3:20 a.m.
NEDg Description generation batch_69c0b27438a08190ab6b72c8fd682bf6 completed March 23, 2026, 3:24 a.m.
NED2 Entity disambiguation (via description) batch_69c0b309a70081908ad3e819879b17e4 completed March 23, 2026, 3:27 a.m.
Created at: March 22, 2026, 3:59 p.m.