Triple
T37541642
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Path of Ascension |
E933338
|
entity |
| Predicate | controlledCharacterType |
P199534
|
FINISHED |
| Object | Kyrian soulbind champion |
—
|
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: Kyrian soulbind champion | Statement: [Path of Ascension, controlledCharacterType, Kyrian soulbind champion]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: controlledCharacterType Context triple: [Path of Ascension, controlledCharacterType, Kyrian soulbind champion]
-
A.
employsCharacterType
Indicates that an entity makes use of or features a particular type or category of character in its content or structure.
-
B.
controllingCharacter
Indicates that one character exerts control, influence, or authority over another character.
-
C.
helpsCharacterType
Indicates that one character type provides assistance or support to another character type.
-
D.
workCharacterType
Indicates that a work involves or features a character of a specified type or role.
-
E.
usedForCharacterType
Indicates that something is intended to be used for, or is suitable for, a particular type of character.
- F. None of above. chosen
Provenance (4 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_69f76ec999288190ae26ec7b6aea7046 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69ff409ff5548190849c2d50e99bd807 |
completed | May 9, 2026, 2:11 p.m. |
| PD | Predicate disambiguation | batch_69ff401a5e188190a72f945e910b4a6c |
completed | May 9, 2026, 2:09 p.m. |
| PDg | Predicate description generation | batch_69ff409ee6ec819088b7c13fabed2ac2 |
completed | May 9, 2026, 2:11 p.m. |
Created at: May 3, 2026, 4:17 p.m.