Triple
T11544783
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Curse of Naxxramas |
E273752
|
entity |
| Predicate | introducesMechanic |
P48192
|
FINISHED |
| Object | Deathrattle synergy |
—
|
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: Deathrattle synergy | Statement: [Curse of Naxxramas, introducesMechanic, Deathrattle synergy]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: introducesMechanic Context triple: [Curse of Naxxramas, introducesMechanic, Deathrattle synergy]
-
A.
featuresMechanic
chosen
Indicates that something includes or incorporates a particular mechanic as part of its design or functionality.
-
B.
mechanismExample
Indicates that one entity serves as an illustrative example of the mechanism or process by which another entity operates or produces an effect.
-
C.
definesMechanism
Indicates that one entity specifies or explains the underlying process or mechanism by which another entity operates or occurs.
-
D.
interactionMechanism
Indicates the process or means by which one entity affects, influences, or interacts with another.
-
E.
mentionsMechanism
Indicates that one entity explicitly refers to or describes the mechanism, process, or causal pathway by which another entity operates or produces an effect.
- 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.