Triple
T22348478
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tang Shaoyi |
E552462
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | 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: Tang | Statement: [Tang Shaoyi, familyName, Tang]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tang Context triple: [Tang Shaoyi, familyName, Tang]
-
A.
Tang
chosen
Tang is a common Chinese surname with historical roots and cultural significance across Chinese-speaking communities.
-
B.
Tang
Tang is a powdered fruit-flavored drink mix, best known for its association with NASA’s early space missions and widespread popularity as an instant beverage.
-
C.
Tang
Tang is the ISO 15924 script code representing the historic Tangut writing system used by the Tangut people of the Western Xia dynasty.
-
D.
Tang dynasty
The Tang dynasty was a powerful and culturally flourishing imperial era of China (618–907 CE) renowned for its advances in art, literature, technology, and cosmopolitan trade along the Silk Road.
-
E.
Tang (state)
Tang (state) was an early Zhou Dynasty vassal state in ancient China that played a role in the political landscape preceding the rise of the Jin state.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e11e4a0ad08190a385b4d343cf6524 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f1579a1c308190ae2174f99ae317ab |
completed | April 29, 2026, 12:58 a.m. |
Created at: April 16, 2026, 8:43 p.m.