Triple
T32495468
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yuanshou |
E830508
|
entity |
| Predicate | emperorPosthumousName |
P91781
|
FINISHED |
| Object | Emperor Wu |
—
|
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: Emperor Wu | Statement: [Yuanshou, emperorPosthumousName, Emperor Wu]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: emperorPosthumousName Context triple: [Yuanshou, emperorPosthumousName, Emperor Wu]
-
A.
hasEmperorPosthumousName
chosen
Indicates that an individual has been granted or is known by a specific posthumous name used for emperors.
-
B.
reigningEmperorPersonalName
Indicates the personal name of the individual who is currently serving as the reigning emperor.
-
C.
rulingEmperorPersonalName
Indicates that the specified personal name belongs to the individual who is (or was) serving as the ruling emperor.
-
D.
hasEmperorTempleName
Indicates that an emperor is associated with a specific posthumous temple name used in imperial ancestral worship.
-
E.
hasEmperorPersonalName
Indicates that the specified personal name is the official emperor’s given name borne by the referenced individual.
- 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_69f349219cb8819087e120f509629c1b |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f6c40e16d0819084ab23950b416eb6 |
completed | May 3, 2026, 3:42 a.m. |
| PD | Predicate disambiguation | batch_69f6bd25bed08190befcabd3a41ffadf |
completed | May 3, 2026, 3:12 a.m. |
Created at: May 1, 2026, 12:59 a.m.