Triple
T13482373
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hikaru Genji |
E318402
|
entity |
| Predicate | fictionalMother |
P45914
|
FINISHED |
| Object |
Lady Kiritsubo
Lady Kiritsubo is a low-ranking but beloved consort of the emperor and the mother of Hikaru Genji in Murasaki Shikibu’s classic Japanese novel "The Tale of Genji."
|
E1043126
|
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: Lady Kiritsubo | Statement: [Hikaru Genji, fictionalMother, Lady Kiritsubo]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lady Kiritsubo Context triple: [Hikaru Genji, fictionalMother, Lady Kiritsubo]
-
A.
Yuriko
Yuriko is the given name of Japanese actress Rinko Kikuchi, known for her roles in films such as "Babel" and "Pacific Rim."
-
B.
Nijō Motoko
Nijō Motoko was a Japanese noblewoman of the Nijō family and the mother of Empress Teimei, consort of Emperor Taishō.
-
C.
Yoriko
Yoriko is a Japanese feminine given name commonly borne by women and girls in Japan.
-
D.
Kodama Naoko
Kodama Naoko is a Japanese individual notable enough to be recognized as a prominent bearer of the surname Kodama.
-
E.
Miyuki Shirogane
Miyuki Shirogane is the diligent and sharp-tongued student council president who serves as one of the central romantic leads in the manga and anime series "Kaguya-sama: Love Is War."
- 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: Lady Kiritsubo Triple: [Hikaru Genji, fictionalMother, Lady Kiritsubo]
Generated description
Lady Kiritsubo is a low-ranking but beloved consort of the emperor and the mother of Hikaru Genji in Murasaki Shikibu’s classic Japanese novel "The Tale of Genji."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Lady Kiritsubo Target entity description: Lady Kiritsubo is a low-ranking but beloved consort of the emperor and the mother of Hikaru Genji in Murasaki Shikibu’s classic Japanese novel "The Tale of Genji."
-
A.
Yuriko
Yuriko is the given name of Japanese actress Rinko Kikuchi, known for her roles in films such as "Babel" and "Pacific Rim."
-
B.
Nijō Motoko
Nijō Motoko was a Japanese noblewoman of the Nijō family and the mother of Empress Teimei, consort of Emperor Taishō.
-
C.
Yoriko
Yoriko is a Japanese feminine given name commonly borne by women and girls in Japan.
-
D.
Kodama Naoko
Kodama Naoko is a Japanese individual notable enough to be recognized as a prominent bearer of the surname Kodama.
-
E.
Miyuki Shirogane
Miyuki Shirogane is the diligent and sharp-tongued student council president who serves as one of the central romantic leads in the manga and anime series "Kaguya-sama: Love Is War."
- 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_69d806b6bfec819089222715b2e86c8e |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69dbaf3868ec8190a6a1803018d4f2d8 |
completed | April 12, 2026, 2:42 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f74635145c8190a42199fe4ed8c2a5 |
completed | May 3, 2026, 12:57 p.m. |
| NEDg | Description generation | batch_69f748dfd4f081908fd5d77fe70f9db4 |
completed | May 3, 2026, 1:08 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69f74965c53081909c662f7f991849bf |
completed | May 3, 2026, 1:11 p.m. |
Created at: April 9, 2026, 9:42 p.m.