Triple
T4605337
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 小和田雅子 |
E100417
|
entity |
| Predicate | 母親 |
P45555
|
FINISHED |
| Object |
小和田優美子
小和田優美子は、日本の皇后雅子さま(小和田雅子)の実母として知られる人物である。
|
E456042
|
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: 小和田優美子 | Statement: [小和田雅子, 母親, 小和田優美子]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: 小和田優美子 Context triple: [小和田雅子, 母親, 小和田優美子]
-
A.
小和田雅子
小和田雅子は、日本の皇太子妃を経て現在の皇后であり、外交官出身の高い教養と国際感覚を持つ人物です。
-
B.
岸田裕子
岸田裕子 is the wife of Japanese Prime Minister Fumio Kishida and serves as Japan’s First Lady, known for her diplomatic and cultural engagements at home and abroad.
-
C.
東條 和子
東條 和子 is known as one of the children of former Japanese Prime Minister and World War II military leader Hideki Tojo.
-
D.
井上 成美
井上成美は、第二次世界大戦期に連合艦隊司令長官などを務めた日本海軍の軍人であり、戦後は平和主義的な言動でも知られた人物である。
-
E.
Koyama Mihoko
Koyama Mihoko is a Japanese philanthropist and art collector best known as the founder and patron of the Miho Museum in Shiga Prefecture, 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: 小和田優美子 Triple: [小和田雅子, 母親, 小和田優美子]
Generated description
小和田優美子は、日本の皇后雅子さま(小和田雅子)の実母として知られる人物である。
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: 小和田優美子 Target entity description: 小和田優美子は、日本の皇后雅子さま(小和田雅子)の実母として知られる人物である。
-
A.
小和田雅子
小和田雅子は、日本の皇太子妃を経て現在の皇后であり、外交官出身の高い教養と国際感覚を持つ人物です。
-
B.
岸田裕子
岸田裕子 is the wife of Japanese Prime Minister Fumio Kishida and serves as Japan’s First Lady, known for her diplomatic and cultural engagements at home and abroad.
-
C.
東條 和子
東條 和子 is known as one of the children of former Japanese Prime Minister and World War II military leader Hideki Tojo.
-
D.
井上 成美
井上成美は、第二次世界大戦期に連合艦隊司令長官などを務めた日本海軍の軍人であり、戦後は平和主義的な言動でも知られた人物である。
-
E.
Koyama Mihoko
Koyama Mihoko is a Japanese philanthropist and art collector best known as the founder and patron of the Miho Museum in Shiga Prefecture, Japan.
- F. None of above. chosen
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 母親 Context triple: [小和田雅子, 母親, 小和田優美子]
-
A.
motherIs
Indicates that one entity is the mother (biological or adoptive) of another entity.
-
B.
isMotherOf
chosen
Indicates that one entity is the female parent who has given birth to or legally/ socially parents the other entity.
-
C.
motherFrom
Indicates that one entity is the mother (biological or adoptive) of another entity, specifying a maternal parent-child relationship from the mother to the child.
-
D.
spouseMother
Indicates that one person is the mother of another person’s spouse.
-
E.
motherName
Indicates that the predicate specifies the personal name of an entity’s mother.
- 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_69bd43cce1e08190a07d53af6a9b6c24 |
completed | March 20, 2026, 12:55 p.m. |
| NER | Named-entity recognition | batch_69bd599b1f0881909fd693b81ff44f98 |
completed | March 20, 2026, 2:28 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bdfa6d24808190a4edc426b8b719cd |
completed | March 21, 2026, 1:54 a.m. |
| NEDg | Description generation | batch_69bdfbea628c81908f96e706d650ef9f |
completed | March 21, 2026, 2:01 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69bdfc97fc54819093e0cff18a40bde2 |
completed | March 21, 2026, 2:04 a.m. |
| PD | Predicate disambiguation | batch_69bd522e2d5c8190937d0b5574f78f99 |
completed | March 20, 2026, 1:57 p.m. |
Created at: March 20, 2026, 1:12 p.m.