Triple
T22267633
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tenson kōrin |
E550390
|
entity |
| Predicate | hasDestinationRealmType |
P117281
|
FINISHED |
| Object | earthly world |
—
|
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: earthly world | Statement: [Tenson kōrin, hasDestinationRealmType, earthly world]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasDestinationRealmType Context triple: [Tenson kōrin, hasDestinationRealmType, earthly world]
-
A.
hasDestinationRegion
Indicates that something is directed, sent, or intended to arrive at a particular geographic or logical region as its destination.
-
B.
isTypeOfDestination
chosen
Indicates that one entity serves as a classification or category describing the kind or type of destination that another entity represents.
-
C.
hasDestinationState
Indicates that an entity is associated with, directed toward, or results in a particular destination state or condition.
-
D.
isDestinationFor
Indicates that one entity serves as the endpoint or target location that another entity is intended to reach or be directed toward.
-
E.
hasPrivateDestination
Indicates that an entity is associated with a destination that is not publicly accessible or is intended for restricted/private use.
- 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_69e11e43d8208190aff4f9cf7f2c2a8a |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f141bd0ea88190b3574883b695d56c |
completed | April 28, 2026, 11:24 p.m. |
| PD | Predicate disambiguation | batch_69e72ff0363081909f794d19c8a64837 |
completed | April 21, 2026, 8:06 a.m. |
Created at: April 16, 2026, 8:39 p.m.