Triple
T18731328
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Farewell (2019 film) |
E458040
|
entity |
| Predicate | leadRoleName |
P12885
|
FINISHED |
| Object | Billi |
—
|
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: Billi | Statement: [The Farewell (2019 film), leadRoleName, Billi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Billi Context triple: [The Farewell (2019 film), leadRoleName, Billi]
-
A.
Billi
chosen
Billi is the young Chinese-American woman at the heart of the film "The Farewell," struggling between cultural traditions and personal honesty as her family hides her grandmother’s terminal diagnosis.
-
B.
Bille
The Bille is a small river in northern Germany that flows through the city of Hamburg and into the Elbe.
-
C.
Bille
Bille is the given name of Australian actor and playwright Bille Brown.
-
D.
Billie
Billie is the nickname of Billie Frechette, a Native American woman best known as the companion of notorious American bank robber John Dillinger during the early 1930s.
-
E.
Billie
Billie is a character known as "Billie the oiler," featured in Stephen Crane’s short story "The Open Boat" as the hardworking seaman who rows the lifeboat.
- 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_69d8d393ba9c8190a8b03b04ddbb0a09 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e56d7854748190b66c4aaadfd67f29 |
completed | April 20, 2026, 12:04 a.m. |
Created at: April 10, 2026, 11:51 a.m.