Triple
T4763755
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | They Drive by Night |
E105758
|
entity |
| Predicate | hasCastMember |
P2308
|
FINISHED |
| Object | Roscoe Karns |
E363410
|
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: Roscoe Karns | Statement: [They Drive by Night, hasCastMember, Roscoe Karns]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Roscoe Karns Context triple: [They Drive by Night, hasCastMember, Roscoe Karns]
-
A.
Roscoe Karns
chosen
Roscoe Karns was an American character actor known for his fast-talking, wisecracking roles in classic Hollywood films of the 1930s and 1940s.
-
B.
Ricardo Cortez
Ricardo Cortez was an American actor of the silent and early sound film era, best known for his leading-man roles in crime dramas and early film noir.
-
C.
Randolph Scott
Randolph Scott was a prominent American film actor best known for his roles in Westerns during the 1930s–1950s.
-
D.
Joel McCrea
Joel McCrea was an American film actor best known for his leading roles in classic Hollywood Westerns and comedies from the 1930s through the 1950s.
-
E.
Warren William
Warren William was an American stage and film actor of the 1930s, best known for his suave, often morally ambiguous leading and supporting roles in Hollywood pre-Code dramas and mysteries.
- 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_69bd43f14cac819081c7c69803648211 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd6530f0648190b76db9964471cfeb |
completed | March 20, 2026, 3:18 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69be43bad99c8190a170baefea057038 |
completed | March 21, 2026, 7:07 a.m. |
Created at: March 20, 2026, 1:20 p.m.