Triple
T29070767
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bloody Mary |
E735808
|
entity |
| Predicate | hasViralResurgence |
P7687
|
FINISHED |
| Object | 2020s TikTok usage |
—
|
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: 2020s TikTok usage | Statement: [Bloody Mary, hasViralResurgence, 2020s TikTok usage]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasViralResurgence Context triple: [Bloody Mary, hasViralResurgence, 2020s TikTok usage]
-
A.
hasViralImpact
Indicates that an entity causes, contributes to, or is associated with rapid, wide-scale spread or influence, similar to how viral content propagates.
-
B.
isViral
Indicates that something spreads rapidly and widely through a population or network, often via person-to-person or user-to-user transmission.
-
C.
hasResurgenceNear
Indicates that an entity experiences a renewed increase, revival, or comeback in close spatial or contextual proximity to another specified entity or location.
-
D.
wentViralOn
chosen
Indicates that content rapidly spread and gained widespread attention or popularity on a particular platform or medium.
-
E.
usesViralVector
Indicates that one entity employs a viral vector as a delivery mechanism or tool to introduce genetic material or components into another entity.
- 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_69f077e9b0a48190bb79548279cb7f64 |
completed | April 28, 2026, 9:03 a.m. |
| NER | Named-entity recognition | batch_69f74c70fd248190a9d5543afcb08211 |
completed | May 3, 2026, 1:24 p.m. |
| PD | Predicate disambiguation | batch_69f7478e3b548190a51d5d436e2bb036 |
completed | May 3, 2026, 1:03 p.m. |
Created at: April 28, 2026, 10:20 a.m.