Triple
T21282178
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Radha Mitchell |
E524552
|
entity |
| Predicate | workedWith |
P398
|
FINISHED |
| Object | Vin Diesel |
—
|
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: Vin Diesel | Statement: [Radha Mitchell, workedWith, Vin Diesel]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Vin Diesel Context triple: [Radha Mitchell, workedWith, Vin Diesel]
-
A.
Vin Diesel
chosen
Vin Diesel is an American actor and producer best known for his role as Dominic Toretto in the Fast & Furious film franchise.
-
B.
Steve Brand
Steve Brand is a central, level-headed suburban resident whose growing paranoia and suspicion drive much of the tension in the classic Twilight Zone episode "The Monsters Are Due on Maple Street."
-
C.
Christopher Martin
Christopher Martin is an American actor and rapper best known as "Play" from the hip-hop duo Kid 'n Play and for his roles in the House Party film series.
-
D.
Sam Jaeger
Sam Jaeger is an American actor best known for his role as Joel Graham on the television drama series "Parenthood."
-
E.
Christopher O’Neal
Christopher O’Neal is an American actor best known for his starring role on the Nickelodeon teen sitcom "How to Rock."
- 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_69e0b5171f6c8190a5d57201ede73811 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e736d249fc8190b0b310467ddeac3c |
completed | April 21, 2026, 8:35 a.m. |
Created at: April 16, 2026, 4:02 p.m.