Triple
T31496992
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Emperor Xianzong of Tang |
E803571
|
entity |
| Predicate | reignAsEmperor |
P10353
|
FINISHED |
| Object | 805–820 |
—
|
LITERAL FINISHED |
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: 805–820 | Statement: [Emperor Xianzong of Tang, reignAsEmperor, 805–820]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: reignAsEmperor Context triple: [Emperor Xianzong of Tang, reignAsEmperor, 805–820]
-
A.
wasEmperorOf
Indicates that one entity held the position and authority of emperor over another entity (typically a state, empire, or territory).
-
B.
reignAs
chosen
Indicates that an entity holds and exercises ruling authority or sovereignty over a domain or people for a period of time.
-
C.
reignAsEmpress
Indicates that a person holds and exercises the supreme imperial authority in the role of empress over a realm or empire.
-
D.
reignAsTitularEmperorStart
Indicates the point in time when an individual begins to hold the title and status of emperor in name, without necessarily exercising actual governing power.
-
E.
successorAsWesternEmperor
Indicates that one individual directly followed another in the role of Western Roman Emperor.
- 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_69f348cae52081909fa8e5f697523ae3 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f7817daf00819098936402e75ab0a6 |
completed | May 3, 2026, 5:10 p.m. |
| PD | Predicate disambiguation | batch_69f780fc5ed88190b7200ee5a29940af |
completed | May 3, 2026, 5:08 p.m. |
Created at: April 30, 2026, 9:41 p.m.