Triple
T37461425
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Xaril, Poisoned Mind |
E930925
|
entity |
| Predicate | heroClassRestriction |
P188671
|
FINISHED |
| Object | can only be used in Rogue decks |
—
|
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: can only be used in Rogue decks | Statement: [Xaril, Poisoned Mind, heroClassRestriction, can only be used in Rogue decks]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: heroClassRestriction Context triple: [Xaril, Poisoned Mind, heroClassRestriction, can only be used in Rogue decks]
-
A.
heroClass
Indicates the character class or role that a hero belongs to within a given system or context.
-
B.
includesLegendaryForEachClass
Indicates that the set or collection contains at least one legendary instance or element corresponding to each distinct class represented.
-
C.
hasChampionClass
Indicates that an entity is associated with, or belongs to, a particular champion class or category.
-
D.
hasAttackRestriction
Indicates that there is a limitation or condition placed on how, when, or whom an entity is allowed to attack.
-
E.
weightClassRestriction
Indicates that an action or relationship is limited or governed by specified weight categories or thresholds.
- 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_69f76ec1a1148190b0a961f188d621b0 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fbacaf54648190811ea33b34907e8e |
completed | May 6, 2026, 9:03 p.m. |
| PD | Predicate disambiguation | batch_69fba883f770819091059c6f6c6af9f7 |
completed | May 6, 2026, 8:45 p.m. |
| PDg | Predicate description generation | batch_69fbacaea12c8190a4c99e64335f0e7e |
completed | May 6, 2026, 9:03 p.m. |
Created at: May 3, 2026, 4:17 p.m.