Triple
T17074971
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Police Story 4: First Strike |
E414324
|
entity |
| Predicate | producer |
P490
|
FINISHED |
| Object | Barbie Tung |
E1245670
|
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: Barbie Tung | Statement: [Police Story 4: First Strike, producer, Barbie Tung]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Barbie Tung Context triple: [Police Story 4: First Strike, producer, Barbie Tung]
-
A.
Barbie Tung
chosen
Barbie Tung is a Hong Kong film producer best known for her work on action movies, including Jackie Chan’s "Rumble in the Bronx."
-
B.
Nikki Chooi
Nikki Chooi is a Canadian violinist acclaimed for his solo, chamber, and orchestral performances, including roles as concertmaster and ensemble member.
-
C.
Bibi Chong
Bibi Chong was the first wife of Tunku Abdul Rahman, the founding Prime Minister of Malaysia.
-
D.
Gabrielle Tana
Gabrielle Tana is a British film producer known for acclaimed dramas such as "Philomena" and other prestige, character-driven films.
-
E.
Barbara Bui
Barbara Bui is a French fashion designer and eponymous luxury label founder known for sleek, rock-chic womenswear and Paris runway collections.
- 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_69d886cef44c8190ba56c44b4e863e64 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3dbc47808819088a4ca039689b213 |
completed | April 18, 2026, 7:30 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a012ede108881909ddd0455be53ffac |
completed | May 11, 2026, 1:20 a.m. |
Created at: April 10, 2026, 5:34 a.m.