Triple
T25804344
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Frances "Frankie" Bergstein |
E649921
|
entity |
| Predicate | platformOfOriginalRelease |
P17946
|
FINISHED |
| Object | Netflix |
—
|
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: Netflix | Statement: [Frances "Frankie" Bergstein, platformOfOriginalRelease, Netflix]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: platformOfOriginalRelease Context triple: [Frances "Frankie" Bergstein, platformOfOriginalRelease, Netflix]
-
A.
originallyAiredOnPlatform
Indicates that a media work was first broadcast or made publicly available on a particular distribution platform.
-
B.
originPlatform
Indicates the platform, system, or environment from which an entity, event, or piece of data originally comes.
-
C.
firstReleasePlatform
chosen
Indicates the platform on which something (such as a product, work, or media) was first released.
-
D.
platformProduced
Indicates that a platform (such as a service, system, or medium) is responsible for creating, generating, or enabling the production of a particular entity or output.
-
E.
originallyReleasedOn
Indicates the date or platform on which something (such as a work, product, or media item) was first made publicly available.
- F. None of above.
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_69e7ab35d264819095367f7e80c983ff |
completed | April 21, 2026, 4:52 p.m. |
| NER | Named-entity recognition | batch_69f6135293908190809e255bf6334760 |
completed | May 2, 2026, 3:08 p.m. |
| PD | Predicate disambiguation | batch_69f611a72780819082f44e66ca2c6ac9 |
completed | May 2, 2026, 3 p.m. |
Created at: April 22, 2026, 7:01 a.m.