Triple
T3843340
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dennis Franz |
E93505
|
entity |
| Predicate | appearedIn |
P795
|
FINISHED |
| Object | Blow Out |
E247482
|
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: Blow Out | Statement: [Dennis Franz, appearedIn, Blow Out]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Blow Out Context triple: [Dennis Franz, appearedIn, Blow Out]
-
A.
Blow Out
chosen
Blow Out is a 1981 neo-noir political thriller film directed by Brian De Palma, known for its suspenseful blend of conspiracy, sound design, and psychological tension.
-
B.
Blow
Blow is a 2001 crime drama film that chronicles the rise and fall of American cocaine smuggler George Jung within the 1970s–1980s drug trade.
-
C.
The Blow
The Blow is an American indie pop band known for its minimalist electronic sound and introspective, narrative-driven lyrics.
-
D.
Man Down
"Man Down" is a song by Barbadian singer Rihanna that blends reggae and R&B influences to tell a dramatic story of remorse after a shooting.
-
E.
Let's Get Blown
"Let's Get Blown" is a smooth, laid-back hip hop single by Snoop Dogg featuring Pharrell, known for its mellow G-funk production and catchy hook.
- 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_69aed96ce578819084ab16e3439976c9 |
completed | March 9, 2026, 2:30 p.m. |
| NER | Named-entity recognition | batch_69aeebb4fd308190a636ba9dbbe57ed6 |
completed | March 9, 2026, 3:48 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b5040f93948190b104cf1b7db671b7 |
completed | March 14, 2026, 6:45 a.m. |
Created at: March 9, 2026, 3:18 p.m.