Triple
T32489074
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Duke of Shanyang |
E830328
|
entity |
| Predicate | successorStateAfterAbdication |
P199372
|
FINISHED |
| Object | Cao Wei |
—
|
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: Cao Wei | Statement: [Duke of Shanyang, successorStateAfterAbdication, Cao Wei]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: successorStateAfterAbdication Context triple: [Duke of Shanyang, successorStateAfterAbdication, Cao Wei]
-
A.
afterAbdication
Indicates that one event, state, or action occurs subsequent to the abdication of a person from a position of authority or office.
-
B.
successorAsRegent
Indicates that one entity assumes the role of regent following another, serving as their successor in that governing capacity.
-
C.
successorSovereign
Indicates that one entity becomes the next ruling sovereign following another entity, inheriting their position of supreme authority.
-
D.
successorAsDeFactoRuler
Indicates that one entity becomes the next actual (though not necessarily officially recognized) ruler after another entity.
-
E.
monarchSuccessor
Indicates that one monarch directly follows another in a royal line of succession.
- 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_69f34920aa4081908d8fb0277414b911 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69ff32b88bf48190b45afd1b60cb511c |
completed | May 9, 2026, 1:12 p.m. |
| PD | Predicate disambiguation | batch_69ff3031e18881908927b2ab452de863 |
completed | May 9, 2026, 1:01 p.m. |
| PDg | Predicate description generation | batch_69ff32b6dd448190a7a6ebb76b99d4cc |
completed | May 9, 2026, 1:12 p.m. |
Created at: May 1, 2026, 12:59 a.m.