Triple
T4034582
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sei Shōnagon |
E83795
|
entity |
| Predicate | hasWorkInCanon |
P977
|
FINISHED |
| Object | Japanese classical canon |
—
|
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: Japanese classical canon | Statement: [Sei Shōnagon, hasWorkInCanon, Japanese classical canon]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasWorkInCanon Context triple: [Sei Shōnagon, hasWorkInCanon, Japanese classical canon]
-
A.
inCanonOf
chosen
Indicates that one entity is officially recognized as part of the established canon or authoritative body of works associated with another entity.
-
B.
hasClosedCanon
Indicates that a body of authoritative texts is considered complete and no additional works can be added to it.
-
C.
hasWorkInCollection
Indicates that a work or item is included as part of a particular collection.
-
D.
hasReferenceWork
Indicates that one entity is associated with a reference work (such as a dictionary, encyclopedia, or manual) that provides authoritative information about it.
-
E.
notInCanonOf
Indicates that something is excluded from, or does not belong to, the officially recognized canon of a given work or universe.
- 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_69aed92f7cf0819098e0539bdcc3767f |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aefb11d92481909aaebbc250ff45b9 |
completed | March 9, 2026, 4:53 p.m. |
| PD | Predicate disambiguation | batch_69aef8fe440c819093a7fa22c4ff3f1a |
completed | March 9, 2026, 4:44 p.m. |
Created at: March 9, 2026, 3:36 p.m.