Triple
T29533413
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ikeda clan |
E749267
|
entity |
| Predicate | supportedSideAtSekigahara |
P148259
|
FINISHED |
| Object | Tokugawa side |
E1628376
|
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: Tokugawa side | Statement: [Ikeda clan, supportedSideAtSekigahara, Tokugawa side]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportedSideAtSekigahara Context triple: [Ikeda clan, supportedSideAtSekigahara, Tokugawa side]
-
A.
sideInBattleOfSekigahara
chosen
Indicates that an entity participated as a side or faction in the Battle of Sekigahara.
-
B.
opponentAtSekigahara
Indicates that two entities were opposing sides against each other in the Battle of Sekigahara.
-
C.
resultOfSekigahara
Indicates that the subject entity exists or occurs as a consequence or outcome of the Battle of Sekigahara.
-
D.
roleInBattleOfUji1180
Indicates the specific role or participation an entity had in the historical Battle of Uji in the year 1180.
-
E.
successorAsDaimyoOfHikone
Indicates that one entity became the next daimyō (feudal lord) of Hikone, directly succeeding another in that position.
- F. None of above.
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_69f0bd47abb081909bd6e6a33d770fd8 |
completed | April 28, 2026, 1:59 p.m. |
| NER | Named-entity recognition | batch_6a037c876524819098545e6037d3107d |
completed | May 12, 2026, 7:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a260c366fa8819085ec36e542b9469f |
completed | June 8, 2026, 12:26 a.m. |
| PD | Predicate disambiguation | batch_6a0379e0f3d88190a4ee7b0673f1ef90 |
completed | May 12, 2026, 7:05 p.m. |
Created at: April 28, 2026, 4:55 p.m.