Triple
T11563767
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sombra |
E274202
|
entity |
| Predicate | counterplay |
P100355
|
FINISHED |
| Object | disrupt enemy backline |
—
|
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: disrupt enemy backline | Statement: [Sombra, counterplay, disrupt enemy backline]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: counterplay Context triple: [Sombra, counterplay, disrupt enemy backline]
-
A.
counterattackBy
Indicates that an entity launches a retaliatory attack in response to an initial attack carried out by another entity.
-
B.
counterSlogan
Indicates that one slogan is created or used specifically to oppose, refute, or undermine another slogan.
-
C.
usesCounterpoint
Indicates that one entity employs counterpoint, combining independent melodic lines in a structured, interdependent musical relationship with another.
-
D.
cooperationAgainst
Indicates a collaborative relationship in which two or more entities work together in opposition to a shared target or adversary.
-
E.
containsCounterpoint
Indicates that one element includes or incorporates another element that serves as a contrasting or opposing argument, idea, or perspective.
- F. None of above. chosen
Provenance (4 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_69d6aae5ac3c81908d2b0a3a665665b2 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d88dd321f88190a57ecaf079fbbc3f |
completed | April 10, 2026, 5:42 a.m. |
| PD | Predicate disambiguation | batch_69d85dc3fc2c8190bed7e2111301a77c |
completed | April 10, 2026, 2:17 a.m. |
| PDg | Predicate description generation | batch_69d87f2e67108190ac36bf47aac12fa8 |
completed | April 10, 2026, 4:40 a.m. |
Created at: April 8, 2026, 9:37 p.m.