Triple
T37303912
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Arx series |
E926027
|
entity |
| Predicate | typicalMagicSystem |
P68842
|
FINISHED |
| Object | gesture-based rune casting |
—
|
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: gesture-based rune casting | Statement: [Arx series, typicalMagicSystem, gesture-based rune casting]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalMagicSystem Context triple: [Arx series, typicalMagicSystem, gesture-based rune casting]
-
A.
typeOfMagic
Indicates that one entity is a specific category, school, or kind of magic associated with another entity.
-
B.
featuresMagicSystem
Indicates that a work includes or is built around a defined system of magic or supernatural powers.
-
C.
hasMagicSystemElement
chosen
Indicates that an entity’s magic system includes or is characterized by a specific elemental component or aspect.
-
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.
hasRitualSystem
Indicates that an entity possesses or is associated with a structured set of rituals or ceremonial practices.
- 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_69f76eb1bc508190924e9fa5d8acdeb3 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a037c8efcd4819088c2aeead65d93df |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a037a11efc08190bb7cacc1325b4dc6 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:16 p.m.