Triple
T17326199
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 西行 |
E420692
|
entity |
| Predicate | 仕えた人物 |
P68932
|
FINISHED |
| Object |
待賢門院璋子
待賢門院璋子は、平安時代末期の鳥羽天皇の中宮であり、後白河天皇の生母として知られる女院である。
|
E1263496
|
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: 待賢門院璋子 | Statement: [西行, 仕えた人物, 待賢門院璋子]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: 待賢門院璋子 Context triple: [西行, 仕えた人物, 待賢門院璋子]
-
A.
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.
-
B.
彰子
彰子 is the Japanese name of Empress Shōshi, a Heian-period imperial consort of Emperor Ichijō and a prominent cultural patron associated with the court of Murasaki Shikibu.
-
C.
栗林貞子
栗林貞子は、第二次世界大戦中の硫黄島守備隊司令官として知られる日本陸軍大将・栗林忠道の家族の一員である女性である。
-
D.
斎藤春子
斎藤春子は、日本の政治家で第19代内閣総理大臣を務めた斎藤実の妻として知られる人物である。
-
E.
額田王
額田王は、飛鳥時代に活躍した日本の女流歌人で、『万葉集』に多くの歌を残したことで知られる人物である。
- 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: 待賢門院璋子 Triple: [西行, 仕えた人物, 待賢門院璋子]
Generated description
待賢門院璋子は、平安時代末期の鳥羽天皇の中宮であり、後白河天皇の生母として知られる女院である。
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: 待賢門院璋子 Target entity description: 待賢門院璋子は、平安時代末期の鳥羽天皇の中宮であり、後白河天皇の生母として知られる女院である。
-
A.
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.
-
B.
彰子
彰子 is the Japanese name of Empress Shōshi, a Heian-period imperial consort of Emperor Ichijō and a prominent cultural patron associated with the court of Murasaki Shikibu.
-
C.
栗林貞子
栗林貞子は、第二次世界大戦中の硫黄島守備隊司令官として知られる日本陸軍大将・栗林忠道の家族の一員である女性である。
-
D.
斎藤春子
斎藤春子は、日本の政治家で第19代内閣総理大臣を務めた斎藤実の妻として知られる人物である。
-
E.
額田王
額田王は、飛鳥時代に活躍した日本の女流歌人で、『万葉集』に多くの歌を残したことで知られる人物である。
- 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_69d889d3adc881909319f1edb8d2a956 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e439d24e548190a766dd246a4d63d4 |
completed | April 19, 2026, 2:11 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a018c4c2dc08190b60982abc9ac7c9c |
completed | May 11, 2026, 7:59 a.m. |
| NEDg | Description generation | batch_6a018f2358b481908226aa84a7bd9d7f |
completed | May 11, 2026, 8:11 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0190125abc8190ad4d1f500e3513b3 |
completed | May 11, 2026, 8:15 a.m. |
Created at: April 10, 2026, 5:43 a.m.