Triple
T31256763
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sayaka Miki |
E796994
|
entity |
| Predicate | laterTransformsInto |
P65473
|
FINISHED |
| Object | witch |
—
|
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: witch | Statement: [Sayaka Miki, laterTransformsInto, witch]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: laterTransformsInto Context triple: [Sayaka Miki, laterTransformsInto, witch]
-
A.
transformedAfter
Indicates that one entity undergoes a transformation or change at a point in time that occurs after the transformation or change of another entity.
-
B.
transformedIn
Indicates that one entity has been changed, converted, or altered into another state, form, or representation within a specific context or process.
-
C.
bodyTransformedInto
chosen
Indicates that one entity’s physical form is changed or converted into another specified form or entity.
-
D.
laterRewrittenAs
Indicates that an earlier work, version, or expression was subsequently rewritten or replaced by a later one.
-
E.
transformedDuring
Indicates that an entity undergoes a change in form, state, or structure within the duration of a specified event or process.
- 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_69ff2fbae9b48190847eefa1c227d43e |
completed | May 9, 2026, 12:59 p.m. |
| PD | Predicate disambiguation | batch_69ff2f2218048190a32224a648182b5d |
completed | May 9, 2026, 12:57 p.m. |
Created at: April 29, 2026, 9:12 p.m.