Triple
T11247986
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bubble Witch Saga |
E266255
|
entity |
| Predicate | socialFeatures |
P14588
|
FINISHED |
| Object | Facebook leaderboards |
—
|
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: Facebook leaderboards | Statement: [Bubble Witch Saga, socialFeatures, Facebook leaderboards]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: socialFeatures Context triple: [Bubble Witch Saga, socialFeatures, Facebook leaderboards]
-
A.
socialFeature
chosen
Indicates that one entity provides or participates in a social interaction capability or function involving other entities.
-
B.
socialView
Indicates a relationship where one entity views, accesses, or inspects another entity’s social-related information, profile, or activity.
-
C.
socialBase
Indicates a foundational social relationship or structure that underlies or supports interactions between entities.
-
D.
socialMedia
Indicates a relationship where one entity uses, is associated with, or interacts through social networking or content-sharing platforms with another entity.
-
E.
socialContribution
Indicates that an entity engages in actions or provides resources that benefit society or a community beyond its own direct interests.
- 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_69d6aac7953c8190b82caf9d7640fdf9 |
completed | April 8, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69d7e91d1484819098ee6b2efb5316a5 |
completed | April 9, 2026, 5:59 p.m. |
| PD | Predicate disambiguation | batch_69d78793c00481908a3f764b610b77a4 |
completed | April 9, 2026, 11:03 a.m. |
Created at: April 8, 2026, 9:31 p.m.