Triple
T31256764
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sayaka Miki |
E796994
|
entity |
| Predicate | witchFormName |
P18099
|
FINISHED |
| Object | Oktavia von Seckendorff |
—
|
NE NERFINISHED |
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: Oktavia von Seckendorff | Statement: [Sayaka Miki, witchFormName, Oktavia von Seckendorff]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: witchFormName Context triple: [Sayaka Miki, witchFormName, Oktavia von Seckendorff]
-
A.
switchType
Indicates that one entity functions as a specific type or category of switch in relation to another entity.
-
B.
alternativeForm
chosen
Indicates that one entity is an alternative version, variant, or representation of another entity.
-
C.
formsInterchangeBetween
Indicates that one entity creates or establishes an interchange (e.g., a junction, connection, or transfer point) between two or more other entities.
-
D.
switchMethod
Indicates that an entity changes from one method, mode, or procedure to another.
-
E.
crossForm
Indicates that one entity moves from one side of a boundary or area to the opposite side, thereby traversing or passing through a form or region.
- 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_69f224dd5fdc81908a4cd24917b67668 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f69edbb7648190bd89c57e0932eac1 |
completed | May 3, 2026, 1:03 a.m. |
| PD | Predicate disambiguation | batch_69f69d1bf8cc8190a78dfa5ab00daf3a |
completed | May 3, 2026, 12:55 a.m. |
Created at: April 29, 2026, 9:12 p.m.