Triple
T28901422
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Valorant |
E732959
|
entity |
| Predicate | antiCheat |
P109536
|
FINISHED |
| Object | Riot Vanguard |
—
|
NE NERFINISHED |
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: Riot Vanguard | Statement: [Valorant, antiCheat, Riot Vanguard]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: antiCheat Context triple: [Valorant, antiCheat, Riot Vanguard]
-
A.
antiCorruptionGoal
Indicates a goal or objective specifically aimed at preventing, reducing, or eliminating corruption.
-
B.
hasCheatCodes
Indicates that a game or system includes special codes or commands that allow users to bypass normal rules or gain advantages.
-
C.
counterMeasureAgainst
chosen
Indicates a relationship where one entity serves as a response or defensive action intended to prevent, mitigate, or neutralize the effects of another entity.
-
D.
sideDenyingIntrusion
Indicates that one side is actively preventing or rejecting an attempted intrusion by another.
-
E.
antiDopingControl
Indicates that an entity conducts, undergoes, or is associated with procedures to detect and prevent the use of prohibited performance-enhancing substances or methods.
- 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_69f05b08c2008190ac426a035a2ed66d |
completed | April 28, 2026, 7 a.m. |
| NER | Named-entity recognition | batch_69f65aa8deec8190b1eef143e10c9598 |
completed | May 2, 2026, 8:12 p.m. |
| PD | Predicate disambiguation | batch_69f6576487e081908d802f1caf59c423 |
completed | May 2, 2026, 7:58 p.m. |
Created at: April 28, 2026, 8:03 a.m.