Triple
T31271683
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 藤田嗣治 |
E797400
|
entity |
| Predicate | 関連施設 |
P81092
|
FINISHED |
| Object |
ランス・フジタ礼拝堂(ノートル=ダム・ド・ラ・ペ礼拝堂)
ランス・フジタ礼拝堂(ノートル=ダム・ド・ラ・ペ礼拝堂)は、フランスのランスにある画家・藤田嗣治が自らの設計と装飾で手がけたカトリック礼拝堂で、その独特なフレスコ画と内装で知られる宗教建築である。
|
E1953436
|
NE FINISHED |
How this triple was built (2 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: ランス・フジタ礼拝堂(ノートル=ダム・ド・ラ・ペ礼拝堂) | Statement: [藤田嗣治, 関連施設, ランス・フジタ礼拝堂(ノートル=ダム・ド・ラ・ペ礼拝堂)]
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: ランス・フジタ礼拝堂(ノートル=ダム・ド・ラ・ペ礼拝堂) Triple: [藤田嗣治, 関連施設, ランス・フジタ礼拝堂(ノートル=ダム・ド・ラ・ペ礼拝堂)]
Generated description
ランス・フジタ礼拝堂(ノートル=ダム・ド・ラ・ペ礼拝堂)は、フランスのランスにある画家・藤田嗣治が自らの設計と装飾で手がけたカトリック礼拝堂で、その独特なフレスコ画と内装で知られる宗教建築である。
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_69f224de2bbc819081af6c32e1d857b9 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f69dcdbdd8819096addcc316fea3d4 |
completed | May 3, 2026, 12:58 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a296c02d8d881909b060c517a83e0c1 |
completed | June 10, 2026, 1:52 p.m. |
| NEDg | Description generation | batch_6a296d07c1488190a6e252822f8524fd |
completed | June 10, 2026, 1:56 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a299d6014388190973ba4c5f6fadbb3 |
completed | June 10, 2026, 5:22 p.m. |
Created at: April 29, 2026, 9:13 p.m.