Triple
T16065753
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rush Hour 2 |
E389726
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Harris Yulin |
E717231
|
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: Harris Yulin | Statement: [Rush Hour 2, starring, Harris Yulin]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Harris Yulin Context triple: [Rush Hour 2, starring, Harris Yulin]
-
A.
Harris Yulin
chosen
Harris Yulin is an American character actor known for his prolific film and television career, often portraying authoritative or villainous roles in productions such as Scarface, Ghostbusters II, and Buffy the Vampire Slayer.
-
B.
Christie Lee
"Christie Lee" is a song by Billy Joel from his 1983 album "An Innocent Man," known for its rock and roll style and narrative lyrics.
-
C.
Fay Chang
Fay Chang is a computer scientist known for co-authoring the influential Google Bigtable paper on large-scale distributed storage systems.
-
D.
Linda Cho
Linda Cho is a Tony Award–winning costume designer known for her work on major Broadway productions and other theatrical performances.
-
E.
Connie Chung
Connie Chung is an American broadcast journalist and television news anchor known for her work on major U.S. networks and high-profile interviews.
- 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_69d86daf32ec8190a8c0466c8f49c3c0 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e1837bec688190a77ad347600b6bdc |
completed | April 17, 2026, 12:49 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffe47ef6648190bf1fe216e78ef660 |
completed | May 10, 2026, 1:50 a.m. |
Created at: April 10, 2026, 4:57 a.m.