Triple
T31251021
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zhenyuan |
E796816
|
entity |
| Predicate | endReignOf |
P2721
|
FINISHED |
| Object | Emperor Dezong of Tang |
—
|
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 Dezong of Tang | Statement: [Zhenyuan, endReignOf, Emperor Dezong of Tang]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: endReignOf Context triple: [Zhenyuan, endReignOf, Emperor Dezong of Tang]
-
A.
endOfReign
chosen
Indicates the point in time or event at which a ruler’s or leader’s period of authority or reign concludes.
-
B.
endOfSecondReign
Indicates that a second period of rule or governance by an entity has concluded.
-
C.
latestReignEnd
Indicates the date or time when the most recent reign or period of rule by an entity came to an end.
-
D.
thirdHolderReignEnd
Indicates the date or point in time when the reign or tenure of the third holder of a title, office, or position comes to an end.
-
E.
concludedDuringReignOf
Indicates that an event, process, or state came to an end while a particular ruler’s reign or period of authority was ongoing.
- 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_69f224dc84d0819081f1cb6f9127e6b1 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f69edbb7648190bd89c57e0932eac1 |
completed | May 3, 2026, 1:03 a.m. |
| PD | Predicate disambiguation | batch_69f69d1bf8cc8190a78dfa5ab00daf3a |
completed | May 3, 2026, 12:55 a.m. |
Created at: April 29, 2026, 9:11 p.m.