Triple
T7025039
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | André De Toth |
E162921
|
entity |
| Predicate | directorOf |
P537
|
FINISHED |
| Object | Crime Wave |
E113569
|
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: Crime Wave | Statement: [André De Toth, directorOf, Crime Wave]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Crime Wave Context triple: [André De Toth, directorOf, Crime Wave]
-
A.
Crime Wave
chosen
Crime Wave is a 1953 film noir crime drama starring Sterling Hayden as a tough police detective pursuing an ex-convict drawn back into a world of robbery and violence.
-
B.
Sky Crime
Sky Crime is a British pay television channel from Sky dedicated to true crime documentaries and series.
-
C.
Murder City
"Murder City" is a punk rock song by Green Day from their politically charged concept album *21st Century Breakdown*.
-
D.
The Criminals
The Criminals is a punk rock band known for featuring guitarist Jason White, who later gained prominence with Green Day.
-
E.
Crime Pays
Crime Pays is a 2009 studio album by Harlem rapper Cam'ron, known for its gritty street narratives and return-to-form sound.
- 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_69c6885b26248190a857541e3d10e299 |
completed | March 27, 2026, 1:38 p.m. |
| NER | Named-entity recognition | batch_69c6e1fb8f0c8190b15dd7ce7ab6a8f2 |
completed | March 27, 2026, 8 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c78857d23c8190904a90459a802cb8 |
completed | March 28, 2026, 7:50 a.m. |
Created at: March 27, 2026, 2:35 p.m.