Triple
T19898932
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sanjo Sanetomi |
E478227
|
entity |
| Predicate | successorAsDaijoDaijin |
P137750
|
FINISHED |
| Object | Kuroda Kiyotaka |
—
|
NE NERFINISHED |
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: Kuroda Kiyotaka | Statement: [Sanjo Sanetomi, successorAsDaijoDaijin, Kuroda Kiyotaka]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: successorAsDaijoDaijin Context triple: [Sanjo Sanetomi, successorAsDaijoDaijin, Kuroda Kiyotaka]
-
A.
successorAsDaimyoOfHikone
Indicates that one entity became the next daimyō (feudal lord) of Hikone, directly succeeding another in that position.
-
B.
successorInJapan
Indicates that one entity directly follows or replaces another in a role, position, or sequence within the context of Japan.
-
C.
successorAsSeniorEmperor
Indicates that one entity becomes the next holder of the position of senior emperor after another entity.
-
D.
successorAsChiefImperialLady
Indicates that one person becomes the next holder of the position of Chief Imperial Lady after another person.
-
E.
successorAsLordOf
Indicates that one entity takes over the role or title of lord from another entity, becoming their direct successor in that lordship.
- F. None of above. chosen
Provenance (4 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_69d8e520682081909892916424699bd5 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e6593fbb348190afa7acf45af406ed |
completed | April 20, 2026, 4:50 p.m. |
| PD | Predicate disambiguation | batch_69e537ecda248190895c96afb6243823 |
completed | April 19, 2026, 8:15 p.m. |
| PDg | Predicate description generation | batch_69e543c136b081909cab9394b958390a |
completed | April 19, 2026, 9:06 p.m. |
Created at: April 10, 2026, 1:52 p.m.