Triple
T37463648
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dragoncaller Alanna |
E930980
|
entity |
| Predicate | deckArchetypeSynergy |
P187926
|
FINISHED |
| Object | Big Spell Mage |
—
|
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: Big Spell Mage | Statement: [Dragoncaller Alanna, deckArchetypeSynergy, Big Spell Mage]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: deckArchetypeSynergy Context triple: [Dragoncaller Alanna, deckArchetypeSynergy, Big Spell Mage]
-
A.
deckArchetype
chosen
Indicates a classification relationship where a specific deck is associated with a particular strategic archetype or style of play.
-
B.
deckStrength
Indicates the relative power or effectiveness of a deck in a game or competitive setting.
-
C.
cardGameCompanionOf
Indicates that one entity regularly accompanies or partners with another specifically for playing card games.
-
D.
deckbuildingConstraint
Indicates a rule or limitation that governs how components (such as cards or items) may be selected, combined, or included when constructing a deck or similar collection.
-
E.
raceSynergy
Indicates how the combination of different races or species enhances, modifies, or interacts to affect overall effectiveness or outcome.
- 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.