Triple
T11984134
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John August |
E285233
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Scriptnotes podcast |
E800721
|
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: Scriptnotes podcast | Statement: [John August, notableWork, Scriptnotes podcast]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Scriptnotes podcast Context triple: [John August, notableWork, Scriptnotes podcast]
-
A.
Scriptnotes podcast
chosen
Scriptnotes podcast is a weekly show about the craft and business of screenwriting, co-hosted by screenwriters Craig Mazin and John August.
-
B.
Story Tap
Story Tap is a digital platform or application that provides users with access to the Sea of Stories content.
-
C.
Pocket Casts
Pocket Casts is a popular cross-platform podcast app known for its powerful discovery tools, playback controls, and syncing across devices.
-
D.
Editors’ Lab
Editors’ Lab is a specialized training program of the Canadian Film Centre that focuses on developing the creative and technical skills of film and media editors.
-
E.
Wistia
Wistia is a video hosting and marketing platform focused on helping businesses create, manage, and analyze video content for sales and marketing.
- 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_69d6ab44a77c8190a652f4b27164e4ef |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d903973c848190aac871d6dfecc74b |
completed | April 10, 2026, 2:05 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f472286edc8190ac72d7dd2b646c91 |
completed | May 1, 2026, 9:28 a.m. |
Created at: April 8, 2026, 9:46 p.m.