Triple
T15702295
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Up in Smoke |
E380621
|
entity |
| Predicate | writer |
P1360
|
FINISHED |
| Object | Tommy Chong |
E197221
|
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: Tommy Chong | Statement: [Up in Smoke, writer, Tommy Chong]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tommy Chong Context triple: [Up in Smoke, writer, Tommy Chong]
-
A.
Tommy Chong
chosen
Tommy Chong is a Canadian-American comedian, actor, and musician best known as half of the stoner comedy duo Cheech & Chong.
-
B.
Exene Cervenka
Exene Cervenka is an American singer, poet, and visual artist best known as the co-lead vocalist of the influential Los Angeles punk band X.
-
C.
Chubbs Peterson
Chubbs Peterson is a fictional former golf pro and mentor character from the comedy film "Happy Gilmore," portrayed by actor Carl Weathers.
-
D.
Dick Tufeld
Dick Tufeld was an American voice actor best known as the iconic voice of the Robot in the classic television series "Lost in Space."
-
E.
Michael McKean
Michael McKean is an American actor, comedian, and musician best known for his roles in "This Is Spinal Tap," the sitcom "Laverne & Shirley," and the television series "Better Call Saul."
- 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_69d86d99e860819094b6957cde470f2c |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e04f6e965881909319f85c51c6fb74 |
completed | April 16, 2026, 2:54 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff7577a3348190912fad48f7d8599e |
completed | May 9, 2026, 5:57 p.m. |
Created at: April 10, 2026, 4:45 a.m.