Triple
T14196072
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 桂小五郎 |
E351837
|
entity |
| Predicate | 配偶者の別名 |
P32626
|
FINISHED |
| Object |
幾松
幾松は、幕末期の志士・桂小五郎(後の木戸孝允)の愛妾として知られる京都の芸妓で、のちに正式な妻となった女性である。
|
E1084909
|
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: 幾松 | Statement: [桂小五郎, 配偶者の別名, 幾松]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: 幾松 Context triple: [桂小五郎, 配偶者の別名, 幾松]
-
A.
秀樹
秀樹 is a common Japanese masculine given name, typically read as "Hideki" and written with kanji meaning "excellent" or "outstanding" and "tree."
-
B.
於茂登岳
於茂登岳 is the highest mountain on Ishigaki Island in Okinawa Prefecture, Japan, known for its subtropical forests and panoramic views of the surrounding islands.
-
C.
紙山
紙山 is a Japanese surname and place name written with the characters for “paper” and “mountain.”
-
D.
摺鉢山
摺鉢山 is the Japanese name for Mount Suribachi, the small volcanic peak on Iwo Jima famous as the site of a pivotal World War II battle and the iconic flag-raising photograph.
-
E.
蓮舫
蓮舫は、日本の政治家であり、参議院議員として活動しつつ野党の要職も歴任してきた人物です。
- 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: 幾松 Triple: [桂小五郎, 配偶者の別名, 幾松]
Generated description
幾松は、幕末期の志士・桂小五郎(後の木戸孝允)の愛妾として知られる京都の芸妓で、のちに正式な妻となった女性である。
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: 幾松 Target entity description: 幾松は、幕末期の志士・桂小五郎(後の木戸孝允)の愛妾として知られる京都の芸妓で、のちに正式な妻となった女性である。
-
A.
秀樹
秀樹 is a common Japanese masculine given name, typically read as "Hideki" and written with kanji meaning "excellent" or "outstanding" and "tree."
-
B.
於茂登岳
於茂登岳 is the highest mountain on Ishigaki Island in Okinawa Prefecture, Japan, known for its subtropical forests and panoramic views of the surrounding islands.
-
C.
紙山
紙山 is a Japanese surname and place name written with the characters for “paper” and “mountain.”
-
D.
摺鉢山
摺鉢山 is the Japanese name for Mount Suribachi, the small volcanic peak on Iwo Jima famous as the site of a pivotal World War II battle and the iconic flag-raising photograph.
-
E.
蓮舫
蓮舫は、日本の政治家であり、参議院議員として活動しつつ野党の要職も歴任してきた人物です。
- F. None of above. chosen
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 配偶者の別名 Context triple: [桂小五郎, 配偶者の別名, 幾松]
-
A.
spouseAlsoKnownAs
chosen
Indicates that a person’s spouse is referred to by an alternative name or alias.
-
B.
spouse name
Indicates that one entity is the legally recognized husband or wife of the other, specifying the partner’s name in a marital relationship.
-
C.
spousePersonalName
Indicates the personal name of a person’s spouse in the relationship.
-
D.
hasNamesakeSpouse
Indicates that one entity has a spouse who shares the same name as another specified entity.
-
E.
spouseGivenName
Indicates that the value is the given (first) name of a person's spouse in the relationship.
- 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_69d827894ac0819097803e57f3227b23 |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de61e1fbd48190a4864fa4443f8f29 |
completed | April 14, 2026, 3:48 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd194b32d88190aa74eef576152db3 |
completed | May 7, 2026, 10:59 p.m. |
| NEDg | Description generation | batch_69fd1ab3f83881908113259c23fe1028 |
completed | May 7, 2026, 11:05 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69fd1b87a0c48190a68367525ed9d2cb |
completed | May 7, 2026, 11:08 p.m. |
| PD | Predicate disambiguation | batch_69de05baed64819096590e5618a3a8ed |
completed | April 14, 2026, 9:15 a.m. |
Created at: April 10, 2026, 1:04 a.m.