Triple
T24322823
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kobayakawa Hideaki |
E613014
|
entity |
| Predicate | commandedTroopsAt |
P155552
|
FINISHED |
| Object | Battle of Sekigahara |
—
|
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: Battle of Sekigahara | Statement: [Kobayakawa Hideaki, commandedTroopsAt, Battle of Sekigahara]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: commandedTroopsAt Context triple: [Kobayakawa Hideaki, commandedTroopsAt, Battle of Sekigahara]
-
A.
commandedForcesOf
Indicates that one entity held command authority over the military or armed forces associated with another entity.
-
B.
commandedForcesFrom
Indicates that one entity held command authority over military or organizational forces originating from another entity.
-
C.
commandingForceSize
Indicates the size or magnitude of the military or organizational force that is exercising command or control in a given context.
-
D.
suppliedTroopsTo
Indicates that one entity provided military personnel or forces to another entity.
-
E.
numberOfUnitsCommanded
Indicates the quantity of units that an entity is in command of within a given context.
- 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_69e2d7da491c8190b6e6218af50923db |
completed | April 18, 2026, 1:01 a.m. |
| NER | Named-entity recognition | batch_69f292ad4cc881908794b501cf70b7a1 |
completed | April 29, 2026, 11:22 p.m. |
| PD | Predicate disambiguation | batch_69f1c45f45888190a9ccc225906c34bd |
completed | April 29, 2026, 8:42 a.m. |
| PDg | Predicate description generation | batch_69f1c6d4e99081909f61899eccafb73e |
completed | April 29, 2026, 8:52 a.m. |
Created at: April 18, 2026, 1:52 a.m.