Triple
T38110631
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Galakrond, the Wretched |
E951643
|
entity |
| Predicate | hasCardTextTheme |
P114955
|
FINISHED |
| Object | Summoning random demons |
—
|
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: Summoning random demons | Statement: [Galakrond, the Wretched, hasCardTextTheme, Summoning random demons]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCardTextTheme Context triple: [Galakrond, the Wretched, hasCardTextTheme, Summoning random demons]
-
A.
cardTheme
chosen
Indicates the thematic style or visual motif associated with a card in relation to its content or context.
-
B.
cardColor
Indicates the color attribute assigned to a card in the relationship.
-
C.
hasLanguageTheme
Indicates that something (such as a work, resource, or item) centrally involves, focuses on, or is characterized by a particular language or linguistic aspect as a thematic element.
-
D.
isThemedTo
Indicates that one entity is designed, styled, or conceptually based around the subject, motif, or theme represented by another entity.
-
E.
hasRankTheme
Indicates that one entity has a thematic role or subject matter characterized by a particular rank or hierarchical level.
- 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_69f76f065ed08190bdfb1b6d817f5b39 |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_6a0048697bd081909073640666ca6a96 |
completed | May 10, 2026, 8:57 a.m. |
| PD | Predicate disambiguation | batch_6a0047bf3c248190a9ac97a7afdfe2cb |
completed | May 10, 2026, 8:54 a.m. |
Created at: May 3, 2026, 4:21 p.m.