Triple
T28784379
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sima Zhao |
E726758
|
entity |
| Predicate | predecessorAsRegent |
P129385
|
FINISHED |
| Object | Sima Shi |
—
|
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: Sima Shi | Statement: [Sima Zhao, predecessorAsRegent, Sima Shi]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: predecessorAsRegent Context triple: [Sima Zhao, predecessorAsRegent, Sima Shi]
-
A.
predecessorAsDeFactoRuler
Indicates that one entity previously held actual ruling power over a domain or group, regardless of formal title, before another entity assumed that de facto control.
-
B.
predecessorAsKing
Indicates that one entity previously held the position of king immediately before the other entity.
-
C.
predecessorAsCoRuler
Indicates that one entity previously shared ruling authority with another entity before being succeeded in that co-ruler position.
-
D.
successorAsRegent
Indicates that one entity assumes the role of regent following another, serving as their successor in that governing capacity.
-
E.
precededByAsRegent
chosen
Indicates that one entity previously served as regent before another entity, in a directly preceding position of regency.
- 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_69f757898fe48190b124dc7301672623 |
completed | May 3, 2026, 2:11 p.m. |
| PD | Predicate disambiguation | batch_69f754c484348190948d2a04ff228fb1 |
completed | May 3, 2026, 1:59 p.m. |
Created at: April 28, 2026, 6:20 a.m.