Triple
T19452439
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jenji Kohan |
E486644
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | The Job |
—
|
NE NERFINISHED |
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: The Job | Statement: [Jenji Kohan, notableWork, The Job]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: The Job Context triple: [Jenji Kohan, notableWork, The Job]
-
A.
The Job
The Job is a film featuring actor John Ortiz in a significant role.
-
B.
The Job
chosen
The Job is a television series produced by DreamWorks Television, best known as a darkly comedic workplace drama centered on the personal and professional struggles of its main characters.
-
C.
The Job
"The Job" is a comedic crime novel co-written by Janet Evanovich and Lee Goldberg, featuring con artist Nicolas Fox and FBI agent Kate O’Hare in a high-stakes heist adventure.
-
D.
A Job to Live
A Job to Live is a work by British politician and author Shirley Williams that reflects her engagement with social and political issues.
-
E.
The Worker
"The Worker" is a 1932 philosophical and political treatise by Ernst Jünger that explores the figure of the worker as the central type of a new, technologically driven and militarized modern age.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8e8d86d608190bd199a98d0297f27 |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e63392aab08190aab09b7c356e5b10 |
completed | April 20, 2026, 2:09 p.m. |
Created at: April 10, 2026, 1:38 p.m.