Triple
T36929549
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Snapchat Spotlight |
E913438
|
entity |
| Predicate | contentRankingBasis |
P7476
|
FINISHED |
| Object | user interactions |
—
|
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: user interactions | Statement: [Snapchat Spotlight, contentRankingBasis, user interactions]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: contentRankingBasis Context triple: [Snapchat Spotlight, contentRankingBasis, user interactions]
-
A.
rankingBasis
chosen
Indicates the criterion or standard used to determine the order or rank of entities in a ranking.
-
B.
rankingScope
Indicates the context or domain within which a ranking is defined, interpreted, or applied.
-
C.
relatedRanking
Indicates a relationship where one item’s ranking is connected to or influenced by another item’s ranking.
-
D.
rankingImpact
Indicates how an entity’s position or level in a ranking is affected or influenced by another factor or action.
-
E.
targetAudienceRank
Indicates the relative priority or importance level assigned to a particular audience segment compared to other potential audiences.
- 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_69fcec5f8b448190b48330a19b462d24 |
completed | May 7, 2026, 7:47 p.m. |
| PD | Predicate disambiguation | batch_69fceaf1e23881908ca24160a638e329 |
completed | May 7, 2026, 7:41 p.m. |
Created at: May 3, 2026, 4:13 p.m.