Triple
T11544309
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mage (Hearthstone class) |
E273743
|
entity |
| Predicate | hasKeywordSynergy |
P65488
|
FINISHED |
| Object | Spell Damage |
—
|
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: Spell Damage | Statement: [Mage (Hearthstone class), hasKeywordSynergy, Spell Damage]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasKeywordSynergy Context triple: [Mage (Hearthstone class), hasKeywordSynergy, Spell Damage]
-
A.
associatedKeyword
chosen
Indicates that one entity is linked to or characterized by a particular keyword used for identification, categorization, or retrieval.
-
B.
hasKeyWork
Indicates that an entity possesses or is associated with a primary or central work (such as a main publication, artwork, or project) that is especially representative or important.
-
C.
hasKeyNotion
Indicates that one entity embodies or contains a central or fundamental concept relevant to another entity.
-
D.
areKeyTo
Indicates that something is essential or critically important for enabling, achieving, or understanding something else.
-
E.
hasKeyBusiness
Indicates that one entity possesses or is associated with a primary or strategically important business of 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_69d6aae4dfa48190a3ab0b19a159a3c5 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d886e1d754819089f3b6be3404fa0b |
completed | April 10, 2026, 5:13 a.m. |
| PD | Predicate disambiguation | batch_69d8087cbe7c819085680f3d67ccc978 |
completed | April 9, 2026, 8:13 p.m. |
Created at: April 8, 2026, 9:37 p.m.