Triple
T18948843
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wang Tao |
E463589
|
entity |
| Predicate | nameInEnglish |
P3437
|
FINISHED |
| Object | Frank Wang |
—
|
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: Frank Wang | Statement: [Wang Tao, nameInEnglish, Frank Wang]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Frank Wang Context triple: [Wang Tao, nameInEnglish, Frank Wang]
-
A.
Frank Wang
chosen
Frank Wang is a Chinese entrepreneur and engineer best known as the founder and CEO of DJI, the world’s leading consumer drone manufacturer.
-
B.
Paul Song
Paul Song is an American physician and healthcare activist known for his work in progressive politics and as the husband of journalist Lisa Ling.
-
C.
Richard Wang
Richard Wang is a relatively common personal name that may refer to multiple individuals across various professional and academic fields.
-
D.
William Wei
William Wei is a Taiwanese singer-songwriter known for his emotive Mandarin pop ballads and acclaimed musicianship.
-
E.
J-Kwon
J-Kwon is an American rapper best known for his 2004 hit single "Tipsy."
- 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_69d8dcfec90481909e926be9767e5779 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5d541ef18819080b2e253dd23835d |
completed | April 20, 2026, 7:26 a.m. |
Created at: April 10, 2026, noon