Triple
T16073133
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jason Friedberg |
E389913
|
entity |
| Predicate | hasDirected |
P7373
|
FINISHED |
| Object | Superfast! |
E1186656
|
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: Superfast! | Statement: [Jason Friedberg, hasDirected, Superfast!]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Superfast! Context triple: [Jason Friedberg, hasDirected, Superfast!]
-
A.
Superfast!
chosen
Superfast! is a 2015 parody film that spoofs the Fast & Furious franchise, co-written and directed by comedy filmmaker Aaron Seltzer.
-
B.
Speedy
Speedy is a 1928 silent comedy film starring Harold Lloyd, known for its energetic New York City setting and memorable Coney Island and baseball sequences.
-
C.
Quick Fast
"Quick Fast" is a hip-hop track by the California rap duo Audio Push, known for its energetic delivery and West Coast-influenced production.
-
D.
Faster
"Faster" is a track from the Girls Aloud album "On Your Radar," showcasing the group's upbeat pop-dance sound.
-
E.
Faster
Faster is a 2010 American action thriller film starring Dwayne Johnson as an ex-con seeking revenge after his brother’s murder.
- 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_69d86daf32ec8190a8c0466c8f49c3c0 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e183c0390c8190b0da263cccec14e5 |
completed | April 17, 2026, 12:50 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffeb8f12708190956f203a3e58e18b |
completed | May 10, 2026, 2:21 a.m. |
Created at: April 10, 2026, 4:57 a.m.