Triple
T33407436
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sophia Marlowe |
E855473
|
entity |
| Predicate | platformOfDistribution |
P120720
|
FINISHED |
| Object | Netflix streaming service |
—
|
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 streaming service | Statement: [Sophia Marlowe, platformOfDistribution, Netflix streaming service]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: platformOfDistribution Context triple: [Sophia Marlowe, platformOfDistribution, Netflix streaming service]
-
A.
platforms
Indicates that one entity provides or serves as a base, medium, or environment that supports the operation, distribution, or presentation of another entity.
-
B.
distributesToPlatform
chosen
Indicates that an entity allocates or delivers its content, products, or services to a specified platform for availability or use.
-
C.
typicalPlatform
Indicates that something commonly or usually serves as the platform or environment on which another thing operates, appears, or is based.
-
D.
occursOnPlatform
Indicates that an event, action, or process takes place or is carried out on a specified platform.
-
E.
소속플랫폼
Indicates a relationship where an entity is affiliated with, belongs to, or is operated on a particular platform.
- 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_69f3496f04a08190804e56ac5098b8e4 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f6e47f37848190aadb137c81760f1f |
completed | May 3, 2026, 6 a.m. |
| PD | Predicate disambiguation | batch_69f6e3da41948190a4cfe866ce184f73 |
completed | May 3, 2026, 5:57 a.m. |
Created at: May 1, 2026, 1:36 a.m.