Triple
T37465263
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kayn Sunfury |
E931017
|
entity |
| Predicate | ignoresTauntFor |
P187870
|
FINISHED |
| Object | hero attacks |
—
|
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: hero attacks | Statement: [Kayn Sunfury, ignoresTauntFor, hero attacks]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ignoresTauntFor Context triple: [Kayn Sunfury, ignoresTauntFor, hero attacks]
-
A.
canBypassTaunt
chosen
Indicates that an entity is able to ignore or circumvent a taunt effect that would normally force it to target the taunting source.
-
B.
frequentlyTaunts
Indicates that one entity repeatedly mocks, provokes, or ridicules another entity on a regular or frequent basis.
-
C.
hasSignatureTaunt
Indicates that an entity possesses a distinctive, characteristic taunting action or gesture uniquely associated with it.
-
D.
isStickyTaunt
Indicates that one entity persistently provokes or mocks another in a way that metaphorically “sticks,” remaining effective or hard to ignore over time.
-
E.
associatedWithTaunt
Indicates that one entity is linked to, involved in, or characterized by a taunt directed at 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_69f76ec1a1148190b0a961f188d621b0 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fba68077788190b311e027435fcf87 |
completed | May 6, 2026, 8:37 p.m. |
| PD | Predicate disambiguation | batch_69fba34c65ac8190b298f0f00d1dcc0e |
completed | May 6, 2026, 8:23 p.m. |
Created at: May 3, 2026, 4:17 p.m.