Triple
T32458372
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Taishi |
E829493
|
entity |
| Predicate | startReignYearOfEmperorWu |
P35128
|
FINISHED |
| Object | 1st year of Taishi |
—
|
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: 1st year of Taishi | Statement: [Taishi, startReignYearOfEmperorWu, 1st year of Taishi]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: startReignYearOfEmperorWu Context triple: [Taishi, startReignYearOfEmperorWu, 1st year of Taishi]
-
A.
eraNumberInReignOfEmperorWu
Indicates the specific numbered era within the reign period of Emperor Wu to which something (such as a date or event) belongs.
-
B.
traditionalFirstEmperorReignStart
Indicates the traditionally recognized starting date of the first emperor’s reign over a given polity or realm.
-
C.
reigningEmperorAtStart
Indicates that the subject was the emperor in power at the beginning of a specified period or event.
-
D.
firstEmperorToRuleAllChina
Indicates that the subject was the earliest emperor to unify and govern all of China under a single centralized rule.
-
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_69f3491df9288190afc0b23b1d6e72ce |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69ff795d25d08190b7584c72be39d309 |
completed | May 9, 2026, 6:13 p.m. |
| PD | Predicate disambiguation | batch_69ff78a90fbc8190a62c57456dc1d4ad |
completed | May 9, 2026, 6:10 p.m. |
Created at: May 1, 2026, 12:56 a.m.