Triple
T23938953
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Danjo Garan sacred precinct |
E602724
|
entity |
| Predicate | founderReligiousTitle |
P39063
|
FINISHED |
| Object | Kōbō Daishi |
—
|
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: Kōbō Daishi | Statement: [Danjo Garan sacred precinct, founderReligiousTitle, Kōbō Daishi]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: founderReligiousTitle Context triple: [Danjo Garan sacred precinct, founderReligiousTitle, Kōbō Daishi]
-
A.
founderHonorificTitle
Indicates that an entity holds an honorific or ceremonial title specifically in their capacity as a founder.
-
B.
founderTitle
chosen
Indicates the formal role or title held by a person in their capacity as a founder of an organization or entity.
-
C.
religiousTitle
Indicates that one entity holds or is referred to by a specific religious rank, honorific, or clerical title in relation to another entity.
-
D.
founderOfReligionAssociated
Indicates that a person is the founder of a religion with which another entity is associated.
-
E.
founderHonorific
Indicates that an honorific title or respectful designation is used when referring to the founder in this relationship.
- 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_69e2953cf6e081909b8e25a10a52dddc |
completed | April 17, 2026, 8:17 p.m. |
| NER | Named-entity recognition | batch_69f1cfa267b88190a1e7d599f22441e2 |
completed | April 29, 2026, 9:30 a.m. |
| PD | Predicate disambiguation | batch_69f1615518088190a206f54e2fdb14a3 |
completed | April 29, 2026, 1:39 a.m. |
Created at: April 17, 2026, 9:08 p.m.