Triple
T11583978
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Clerks |
E274703
|
entity |
| Predicate | director |
P255
|
FINISHED |
| Object | Kevin Smith |
E131538
|
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: Kevin Smith | Statement: [Clerks, director, Kevin Smith]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kevin Smith Context triple: [Clerks, director, Kevin Smith]
-
A.
Kevin Smith
chosen
Kevin Smith is an American filmmaker, actor, and comic book writer best known for creating the View Askewniverse films such as "Clerks," "Mallrats," and "Dogma."
-
B.
Jon Bokenkamp
Jon Bokenkamp is an American screenwriter and producer best known for creating the television series "The Blacklist" and writing several thriller films.
-
C.
Eli Roth
Eli Roth is an American filmmaker and actor best known for directing horror films like "Hostel" and appearing in Quentin Tarantino's movies.
-
D.
Jason Mewes
Jason Mewes is an American actor and comedian best known for playing the talkative stoner Jay in Kevin Smith’s View Askewniverse films.
-
E.
Evan Goldberg
Evan Goldberg is a technology entrepreneur best known for founding the cloud-based business software company NetSuite.
- 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_69d6aae6b14c81908dc5a74bad7591f9 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d8904db5748190ae5f10ae86ccdf46 |
completed | April 10, 2026, 5:53 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e7142d442c8190a48372e0e17db517 |
completed | April 21, 2026, 6:07 a.m. |
Created at: April 8, 2026, 9:38 p.m.