Triple
T4706453
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | DJI |
E104398
|
entity |
| Predicate | hasKeyPerson |
P256
|
FINISHED |
| Object | Frank Wang |
E463787
|
NE 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: Frank Wang | Statement: [DJI, hasKeyPerson, Frank Wang]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Frank Wang Context triple: [DJI, hasKeyPerson, 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.
J-Kwon
J-Kwon is an American rapper best known for his 2004 hit single "Tipsy."
-
C.
Nima Yooshij
Nima Yooshij was a pioneering Iranian poet widely regarded as the father of modern Persian poetry for revolutionizing its form and style.
-
D.
Jonathan Wang
Jonathan Wang is a film producer best known for his work on the acclaimed, genre-bending movie "Everything Everywhere All at Once."
-
E.
Doug Jung
Doug Jung is an American screenwriter and producer best known for co-writing the science fiction film "Star Trek Beyond."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69bd43eac3c08190af7e4020c6c3704c |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd63e9f0b88190820aa7fba2f91b6e |
completed | March 20, 2026, 3:12 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69be39e6428c81909be9bdb314993b1e |
completed | March 21, 2026, 6:25 a.m. |
Created at: March 20, 2026, 1:17 p.m.