Triple
T31115953
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jianzhong |
E793086
|
entity |
| Predicate | sovereignTitleHolder |
P163921
|
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: [Jianzhong, sovereignTitleHolder, Emperor Dezong of Tang]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sovereignTitleHolder Context triple: [Jianzhong, sovereignTitleHolder, Emperor Dezong of Tang]
-
A.
monarchicTitleHolderOf
chosen
Indicates that one entity holds a monarchic title associated with another entity (such as a realm, position, or office).
-
B.
sovereignTitleUntil
Indicates that an entity held a particular sovereign title or rulership status continuously up to a specified end date or point in time.
-
C.
coSovereignTitle
Indicates that two or more entities share the same sovereign authority or ruling title jointly.
-
D.
sovereigntyHolder
Indicates which entity possesses ultimate governing authority or sovereign control over another entity or territory.
-
E.
headOfStateTitle
Indicates the official title held by the person who serves as the head of state of a country or political entity.
- 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_69f224d0a7688190af3fe3e6e26d01ed |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f69dfdda708190be290c7bec205445 |
completed | May 3, 2026, 12:59 a.m. |
| PD | Predicate disambiguation | batch_69f69d1a37e081908d1d86b90ff502bd |
completed | May 3, 2026, 12:55 a.m. |
Created at: April 29, 2026, 9:04 p.m.