Triple
T34797654
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dunmer |
E1003132
|
entity |
| Predicate | magicUse |
P54235
|
FINISHED |
| Object | conjuration of ancestor spirits |
—
|
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: conjuration of ancestor spirits | Statement: [Dunmer, magicUse, conjuration of ancestor spirits]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: magicUse Context triple: [Dunmer, magicUse, conjuration of ancestor spirits]
-
A.
magicTrigger
Indicates that one entity initiates or activates a magical effect, condition, or event upon another entity or context.
-
B.
usesMagic
chosen
Indicates that an entity performs actions or achieves effects by employing magical powers or supernatural abilities.
-
C.
usesMagicFor
Indicates that one entity employs or applies magic as a means to achieve, affect, or perform something involving another entity or context.
-
D.
spells
Indicates that one entity writes or names the letters of a word or sequence in their correct order for another entity or context.
-
E.
typeOfMagic
Indicates that one entity is a specific category, school, or kind of magic associated with 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_69f76db543808190b188c6c86a91491b |
completed | May 3, 2026, 3:45 p.m. |
| NER | Named-entity recognition | batch_69f77a86050881909fa363fe6984f79f |
completed | May 3, 2026, 4:40 p.m. |
| PD | Predicate disambiguation | batch_69f7795b1abc8190823664d1caa94649 |
completed | May 3, 2026, 4:35 p.m. |
Created at: May 3, 2026, 3:59 p.m.