Triple
T5989790
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kōkyo |
E133315
|
entity |
| Predicate | specialPublicOpening |
P37420
|
FINISHED |
| Object | Emperor’s birthday |
—
|
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: Emperor’s birthday | Statement: [Kōkyo, specialPublicOpening, Emperor’s birthday]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: specialPublicOpening Context triple: [Kōkyo, specialPublicOpening, Emperor’s birthday]
-
A.
notOpenToGeneralPublic
Indicates that access to the subject is restricted and not available to the general public.
-
B.
openedForPublic
Indicates that something has been made accessible or available for use, entry, or participation by the general public.
-
C.
openedToPublicBy
Indicates that an entity was made accessible or available to the general public through the action or decision of another entity.
-
D.
publicExhibitOpened
Indicates that a public exhibition has been officially opened or made accessible to the general public.
-
E.
specialtyEvent
chosen
Indicates that an event is designated as a special or distinctive occurrence, often differing from regular or routine events in nature or purpose.
- 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_69c0087010d081908bb8142342d63330 |
completed | March 22, 2026, 3:19 p.m. |
| NER | Named-entity recognition | batch_69c04dc76fd481908cc3f327e532a1a6 |
completed | March 22, 2026, 8:15 p.m. |
| PD | Predicate disambiguation | batch_69c049de98648190962b14fd341c93da |
completed | March 22, 2026, 7:58 p.m. |
Created at: March 22, 2026, 4:05 p.m.