Triple

T6896697
Position Surface form Disambiguated ID Type / Status
Subject 佳子内親王 E159387 entity
Predicate 父方の祖母 P66167 FINISHED
Object 上皇后美智子
上皇后美智子は、日本の上皇・明仁の皇后として平成時代の象徴的存在となり、民間出身の皇后として国民に広く親しまれた人物である。
E627708 NE FINISHED

How this triple was built (5 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: 上皇后美智子 | Statement: [佳子内親王, 父方の祖母, 上皇后美智子]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: 上皇后美智子
Context triple: [佳子内親王, 父方の祖母, 上皇后美智子]
  • A. 秋篠宮紀子妃
    秋篠宮紀子妃は、日本の皇族で秋篠宮文仁親王妃として知られる、悠仁親王の母である妃殿下です。
  • B. 三笠宮寛仁親王妃信子
    三笠宮寛仁親王妃信子は、日本の皇族である三笠宮寛仁親王の妃であり、政界名門・麻生家の出身としても知られる人物である。
  • C. 香淳皇后
    香淳皇后 was the Empress of Japan as the wife of Emperor Shōwa (Hirohito) and the mother of Emperor Akihito.
  • D. Empress Masako
    Empress Masako is the current Empress of Japan, a Harvard-educated former diplomat known for her international background and marriage to Emperor Naruhito.
  • E. 中山慶子
    中山慶子 was a Japanese noblewoman and lady-in-waiting of the late Edo period, best known as the birth mother of Emperor Meiji.
  • 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: 上皇后美智子
Triple: [佳子内親王, 父方の祖母, 上皇后美智子]
Generated description
上皇后美智子は、日本の上皇・明仁の皇后として平成時代の象徴的存在となり、民間出身の皇后として国民に広く親しまれた人物である。
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: 上皇后美智子
Target entity description: 上皇后美智子は、日本の上皇・明仁の皇后として平成時代の象徴的存在となり、民間出身の皇后として国民に広く親しまれた人物である。
  • A. 秋篠宮紀子妃
    秋篠宮紀子妃は、日本の皇族で秋篠宮文仁親王妃として知られる、悠仁親王の母である妃殿下です。
  • B. 三笠宮寛仁親王妃信子
    三笠宮寛仁親王妃信子は、日本の皇族である三笠宮寛仁親王の妃であり、政界名門・麻生家の出身としても知られる人物である。
  • C. 香淳皇后
    香淳皇后 was the Empress of Japan as the wife of Emperor Shōwa (Hirohito) and the mother of Emperor Akihito.
  • D. Empress Masako
    Empress Masako is the current Empress of Japan, a Harvard-educated former diplomat known for her international background and marriage to Emperor Naruhito.
  • E. 中山慶子
    中山慶子 was a Japanese noblewoman and lady-in-waiting of the late Edo period, best known as the birth mother of Emperor Meiji.
  • F. None of above. chosen
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: 父方の祖母
Context triple: [佳子内親王, 父方の祖母, 上皇后美智子]
  • A. paternal grandmother chosen
    Indicates that one entity is the mother of the other entity’s father.
  • B. ancestorMother
    Indicates that one entity is a female ancestor (mother, grandmother, etc.) of another entity in a family lineage.
  • C. maternalGrandfatherOf
    Indicates that one person is the father of another person's mother.
  • D. stepfatherOf
    Indicates that one person is the male spouse or partner of a child's parent, but is not the child's biological or adoptive father.
  • E. motherFather
    Indicates that the two entities are the biological parents (mother and father) of a child or offspring.
  • F. None of above.

Provenance (6 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_69c6883822e0819091e321526f20ae0a completed March 27, 2026, 1:38 p.m.
NER Named-entity recognition batch_69c6d95ae3f88190b7f5d440f90ae9f9 completed March 27, 2026, 7:24 p.m.
NED1 Entity disambiguation (via context triple) batch_69c748dfd9608190891c8df48b771e20 completed March 28, 2026, 3:20 a.m.
NEDg Description generation batch_69c749d4b088819095f991f976592d04 completed March 28, 2026, 3:24 a.m.
NED2 Entity disambiguation (via description) batch_69c74aab12988190bd23cfcc06c55cde completed March 28, 2026, 3:27 a.m.
PD Predicate disambiguation batch_69c6d7b7681481909ec50509b19fcf81 completed March 27, 2026, 7:17 p.m.
Created at: March 27, 2026, 2:24 p.m.