Triple
T36929521
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Snapchat Spotlight |
E913438
|
entity |
| Predicate | discoveryMechanism |
P7311
|
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: [Snapchat Spotlight, discoveryMechanism, personalized recommendations]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: discoveryMechanism Context triple: [Snapchat Spotlight, discoveryMechanism, personalized recommendations]
-
A.
discoveryMethod
chosen
Indicates the process, technique, or approach by which something was found, detected, or identified.
-
B.
discovery
Indicates the event or process by which one entity finds, uncovers, or identifies something previously unknown or unrecognized.
-
C.
discoveryTarget
Indicates that one entity is the object, subject, or focus that another entity discovers or aims to discover.
-
D.
attributedDiscovery
Indicates that the discovery of something is credited or assigned to a particular agent or entity.
-
E.
discoveryScope
Indicates the extent or range within which something can be found, detected, or identified.
- 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_69f76e896c988190880c130e01303dd4 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fcc7338120819081cb46547d60f2cb |
completed | May 7, 2026, 5:09 p.m. |
| PD | Predicate disambiguation | batch_69fcc58566a0819082d5ea36e03bf0c6 |
completed | May 7, 2026, 5:01 p.m. |
Created at: May 3, 2026, 4:13 p.m.