Triple
T21430224
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Payback |
E528663
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Lucy Liu |
—
|
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: Lucy Liu | Statement: [Payback, starring, Lucy Liu]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lucy Liu Context triple: [Payback, starring, Lucy Liu]
-
A.
Lucy Liu
chosen
Lucy Liu is an American actress and producer known for her versatile roles in film and television, including standout performances in projects like "Ally McBeal," "Kill Bill," and "Elementary."
-
B.
Zoë Chao
Zoë Chao is an American actress and writer known for her work in film and television, including prominent roles in indie comedies and streaming series.
-
C.
Ming-Na Wen
Ming-Na Wen is a Chinese-American actress best known for her roles in projects like ER, Agents of S.H.I.E.L.D., and various Disney productions.
-
D.
Hana Mae Lee
Hana Mae Lee is an American actress, comedian, and fashion designer best known for her role as Lilly in the Pitch Perfect film series.
-
E.
Julia Hsu
Julia Hsu is an actress best known for her role as Soo-Yung, the kidnapped daughter of a Chinese consul, in the action-comedy film "Rush Hour."
- 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_69e0c455f3688190810bc96365791b0f |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69ee813ef6a8819089511b8f608c9491 |
completed | April 26, 2026, 9:18 p.m. |
Created at: April 16, 2026, 5:49 p.m.