Triple
T25673027
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sadaijin |
E643728
|
entity |
| Predicate | rankRelativeToUdaijin |
P152574
|
FINISHED |
| Object | senior to the Udaijin |
—
|
LITERAL 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: senior to the Udaijin | Statement: [Sadaijin, rankRelativeToUdaijin, senior to the Udaijin]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: rankRelativeToUdaijin Context triple: [Sadaijin, rankRelativeToUdaijin, senior to the Udaijin]
-
A.
rankRelativeToDaijō-daijin
Indicates the relative hierarchical rank or status of an entity in comparison to the position of Daijō-daijin (Chancellor of the Realm).
-
B.
rankWithinJapan
Indicates the relative position or standing of something when compared only among counterparts within Japan.
-
C.
rankInJapaneseOrders
Indicates the position or level an entity holds within the hierarchy of Japanese orders, decorations, or honors.
-
D.
rankIn
chosen
Indicates the relative position or level an entity holds within an ordered set, hierarchy, or competitive context.
-
E.
rankGrade
Indicates the grade or level assigned to an entity within a ranking or evaluation system.
- F. None of above.
Provenance (3 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_69e77e7f69808190ad27df1006f6037a |
completed | April 21, 2026, 1:41 p.m. |
| NER | Named-entity recognition | batch_69f5fb3460488190a720fe1f708509f2 |
completed | May 2, 2026, 1:25 p.m. |
| PD | Predicate disambiguation | batch_69f4a0f7c6008190ae8cee3e71e19b94 |
completed | May 1, 2026, 12:47 p.m. |
Created at: April 21, 2026, 7:31 p.m.