Triple
T22033229
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tang Wei |
E544135
|
entity |
| Predicate | starredIn |
P1668
|
FINISHED |
| Object | Speed Angels |
—
|
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: Speed Angels | Statement: [Tang Wei, starredIn, Speed Angels]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Speed Angels Context triple: [Tang Wei, starredIn, Speed Angels]
-
A.
Speed Angels
chosen
Speed Angels is a Chinese action drama film centered on female race car drivers, known in part for featuring actress Tang Wei in its cast.
-
B.
Chrome Angel
Chrome Angel is the central protagonist of the 1977 film "Handle with Care," around whom the movie’s narrative and character dynamics revolve.
-
C.
When Angels Learn To Fly
"When Angels Learn To Fly" is a song by the rock band The Human Condition, featured as one of the tracks on their release.
-
D.
Even Angels
"Even Angels" is a song featured on the album "Back to Me" by American singer Fantasia Barrino.
-
E.
Angels One Five
Angels One Five is a 1952 British war film depicting Royal Air Force fighter operations during the Battle of Britain in World War II.
- 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_69e11e2f98c8819083e11eab90942a78 |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f127ee84848190a22c24bf14498520 |
completed | April 28, 2026, 9:34 p.m. |
Created at: April 16, 2026, 8:24 p.m.