Triple
T28784382
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sima Zhao |
E726758
|
entity |
| Predicate | notableGeneralUnderCommand |
P45509
|
FINISHED |
| Object | Deng Ai |
—
|
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: Deng Ai | Statement: [Sima Zhao, notableGeneralUnderCommand, Deng Ai]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: notableGeneralUnderCommand Context triple: [Sima Zhao, notableGeneralUnderCommand, Deng Ai]
-
A.
notableCommanderUnder
chosen
Indicates that one entity served as a notable military commander under the authority or leadership of another entity.
-
B.
notableCommanderAtAction
Indicates that a particular commander is notably associated with leading or playing a significant command role in a specific action or event.
-
C.
capturedUnderCommandOf
Indicates that one entity was captured while operating under the authority, leadership, or command of another entity.
-
D.
corpsCommandedUnder
Indicates that one military corps was commanded under the authority or control of another specified commander or higher-level unit.
-
E.
notableCommanderOrAlly
Indicates that an entity is a significant military leader or important ally associated with another entity, such as a person, group, or organization.
- 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_69f0319aabec81908368720196f69a35 |
completed | April 28, 2026, 4:03 a.m. |
| NER | Named-entity recognition | batch_6a0186cde2fc819080d7c06503dcc479 |
completed | May 11, 2026, 7:35 a.m. |
| PD | Predicate disambiguation | batch_6a0183ff6d34819080c8ad7c11611a36 |
completed | May 11, 2026, 7:23 a.m. |
Created at: April 28, 2026, 6:20 a.m.