Triple
T31251020
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zhenyuan |
E796816
|
entity |
| Predicate | startReignOf |
P35128
|
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, startReignOf, Emperor Dezong of Tang]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: startReignOf Context triple: [Zhenyuan, startReignOf, Emperor Dezong of Tang]
-
A.
reignStart
Indicates the date or point in time when an entity’s period of ruling or governing authority begins.
-
B.
reignStartAsKing
Indicates the time or event at which an individual begins their reign in the role of king.
-
C.
reignStartAsDeFactoRuler
Indicates the time at which an individual effectively began exercising ruling power in practice, regardless of formal or official recognition.
-
D.
settingReign
Indicates that a particular reign (of a ruler or authority) is associated with or takes place within a specific setting or context.
-
E.
startEmperor
chosen
Indicates that an entity begins its role, reign, or status as an 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_69f224dc84d0819081f1cb6f9127e6b1 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69ff1f3f94fc819095955299f50ab4ce |
completed | May 9, 2026, 11:49 a.m. |
| PD | Predicate disambiguation | batch_69ff1ea47748819082f63d9b9d9c3e65 |
completed | May 9, 2026, 11:46 a.m. |
Created at: April 29, 2026, 9:11 p.m.