Triple
T38586765
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rescue from Thros, the Blighted Lands |
E932362
|
entity |
| Predicate | relatedMagic |
P19914
|
FINISHED |
| Object | death magic |
—
|
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: death magic | Statement: [Rescue from Thros, the Blighted Lands, relatedMagic, death magic]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relatedMagic Context triple: [Rescue from Thros, the Blighted Lands, relatedMagic, death magic]
-
A.
relationshipWithMagic
Indicates a connection or interaction an entity has with magic, such as using, being affected by, or being inherently tied to magical forces.
-
B.
involvesMagic
Indicates that the related action, event, or relationship includes the use or presence of magical powers, forces, or phenomena.
-
C.
magical
Indicates that one entity possesses, uses, or is characterized by supernatural or mystical powers in relation to another entity or context.
-
D.
typeOfMagic
chosen
Indicates that one entity is a specific category, school, or kind of magic associated with another entity.
-
E.
associatedMystic
Indicates a relationship where one entity is linked or connected to another through a mystical, spiritual, or esoteric association.
- 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_69f76ec654d48190b421111cf26e54d9 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a037c903be48190a2fafa53d7d50d42 |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a037a1e32108190897356d6a7fed879 |
completed | May 12, 2026, 7:06 p.m. |
Created at: May 3, 2026, 4:32 p.m.