Triple
T7996787
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Minamoto clan |
E186146
|
entity |
| Predicate | hasKanjiName |
P28734
|
FINISHED |
| Object |
源氏
源氏 is the Japanese reading of the kanji for the Minamoto clan, one of the most prominent and powerful samurai lineages in Japanese history.
|
E702279
|
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: 源氏 | Statement: [Minamoto clan, hasKanjiName, 源氏]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: 源氏 Context triple: [Minamoto clan, hasKanjiName, 源氏]
-
A.
杉本博司
杉本博司は、長時間露光による海景や劇場シリーズなどで知られる、日本出身の世界的に著名な現代美術写真家・美術家です。
-
B.
植木枝盛
植木枝盛 was a prominent Meiji-era Japanese political activist, journalist, and theorist of popular rights who strongly advocated constitutional government and civil liberties.
-
C.
寺内正照
寺内正照は、日本の陸軍軍人・政治家であり第18代内閣総理大臣を務めた寺内正毅の父親として知られる人物である。
-
D.
佐藤
佐藤 is a very common Japanese surname, often romanized as Satō or Sato.
-
E.
潤一郎
潤一郎 is a Japanese given name commonly used for males.
- 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: 源氏 Triple: [Minamoto clan, hasKanjiName, 源氏]
Generated description
源氏 is the Japanese reading of the kanji for the Minamoto clan, one of the most prominent and powerful samurai lineages in Japanese history.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: 源氏 Target entity description: 源氏 is the Japanese reading of the kanji for the Minamoto clan, one of the most prominent and powerful samurai lineages in Japanese history.
-
A.
杉本博司
杉本博司は、長時間露光による海景や劇場シリーズなどで知られる、日本出身の世界的に著名な現代美術写真家・美術家です。
-
B.
植木枝盛
植木枝盛 was a prominent Meiji-era Japanese political activist, journalist, and theorist of popular rights who strongly advocated constitutional government and civil liberties.
-
C.
寺内正照
寺内正照は、日本の陸軍軍人・政治家であり第18代内閣総理大臣を務めた寺内正毅の父親として知られる人物である。
-
D.
佐藤
佐藤 is a very common Japanese surname, often romanized as Satō or Sato.
-
E.
潤一郎
潤一郎 is a Japanese given name commonly used for males.
- F. None of above. chosen
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasKanjiName Context triple: [Minamoto clan, hasKanjiName, 源氏]
-
A.
hasNameInJapanese
chosen
Indicates that an entity is associated with a specific name expressed in the Japanese language.
-
B.
hanjaName
Indicates that one entity is the Sino-Korean (hanja) written form corresponding to the name of another entity.
-
C.
nameLengthInKanji
Indicates the number of kanji characters used in an entity’s name.
-
D.
hasOfficialNameInJapanese
Indicates that an entity has an official, formally recognized name expressed in the Japanese language.
-
E.
hasJavaneseName
Indicates that an entity possesses a name expressed in the Javanese language.
- 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_69ca829c6c308190ab05b43d234c52b2 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb3c97968481908d261b3f0bd6b8e6 |
completed | March 31, 2026, 3:16 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cbe10d5eb081909f257390094de442 |
completed | March 31, 2026, 2:58 p.m. |
| NEDg | Description generation | batch_69cbe4888800819080eb11c9b7b7e28f |
completed | March 31, 2026, 3:13 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69cc1175c8a481909b29d3b850ad9084 |
completed | March 31, 2026, 6:24 p.m. |
| PD | Predicate disambiguation | batch_69cb0483d3b48190b250c7603d747bca |
completed | March 30, 2026, 11:17 p.m. |
Created at: March 30, 2026, 5:17 p.m.