Triple
T25987272
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shudder |
E646235
|
entity |
| Predicate | providesUserFeature |
P203
|
FINISHED |
| Object | personalized recommendations |
—
|
LITERAL 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: personalized recommendations | Statement: [Shudder, providesUserFeature, personalized recommendations]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: providesUserFeature Context triple: [Shudder, providesUserFeature, personalized recommendations]
-
A.
featuresSupporter
Indicates that one entity serves as a supporter, advocate, or promoter of another entity or its cause.
-
B.
supportsFeature
chosen
Indicates that one entity provides, enables, or is compatible with a particular feature or capability of another.
-
C.
userProfileFeatures
Indicates that certain characteristics, settings, or attributes are associated with and define a user's profile.
-
D.
supportsUserServices
Indicates that one entity provides the necessary functionality or resources for user-facing services to operate or be delivered.
-
E.
hasFeatureStatus
Indicates that an entity possesses a particular feature along with its current state or condition.
- 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_69e77e881fc08190ba1c8dc7e2a07f97 |
completed | April 21, 2026, 1:41 p.m. |
| NER | Named-entity recognition | batch_69f67f0488bc819089fbd2d2478158d3 |
completed | May 2, 2026, 10:47 p.m. |
| PD | Predicate disambiguation | batch_69f67e3ed894819094c067c1ef624951 |
completed | May 2, 2026, 10:44 p.m. |
Created at: April 22, 2026, 8:55 a.m.