Triple
T21854742
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2 Broke Girls |
E539593
|
entity |
| Predicate | mainCharacter |
P1183
|
FINISHED |
| Object | Han Lee |
—
|
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: Han Lee | Statement: [2 Broke Girls, mainCharacter, Han Lee]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Han Lee Context triple: [2 Broke Girls, mainCharacter, Han Lee]
-
A.
Han Lee
chosen
Han Lee is a fictional character best known as the blunt, quirky Korean diner owner from the American sitcom "2 Broke Girls."
-
B.
Hoon Lee
Hoon Lee is an American actor and voice actor known for roles in series like Banshee and for voicing characters in animated shows and video games.
-
C.
SangYup Lee
SangYup Lee is a prominent South Korean automobile designer known for leading Hyundai’s global design direction, including acclaimed models like the Ioniq 5.
-
D.
Hong Kim
Hong Kim is a film producer known for working on the animated feature "The Nut Job."
-
E.
Yohan Lee
Yohan Lee is a fictional character from the work "The Encyclopedists."
- 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_69e0c47829648190bbe2d1d7033768ec |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f0bd5ba9288190af962117124f6483 |
completed | April 28, 2026, 1:59 p.m. |
Created at: April 16, 2026, 6:56 p.m.