Triple
T38522603
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Donggyeong Daejeon |
E922527
|
entity |
| Predicate | inReligiousCanonOf |
P59935
|
FINISHED |
| Object | Cheondoism |
—
|
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: Cheondoism | Statement: [Donggyeong Daejeon, inReligiousCanonOf, Cheondoism]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: inReligiousCanonOf Context triple: [Donggyeong Daejeon, inReligiousCanonOf, Cheondoism]
-
A.
religiousCanon
Indicates that something is formally recognized as part of an established body of authoritative religious texts or doctrine.
-
B.
regardedAsScriptureBy
chosen
Indicates that something is considered to be sacred scripture or canonical religious text by a particular person, group, or tradition.
-
C.
inChristianCanonOrder
Indicates that the entities are arranged according to the sequence used in the Christian biblical canon.
-
D.
religiousCanonRelation
Indicates that one entity is part of, derived from, or otherwise related to the officially recognized religious canon of another entity.
-
E.
religiousCanonType
Indicates the specific category or type of religious canon to which a text, rule, or tradition belongs.
- 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_69f76ea5f5588190bd0b28c82e975640 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fcd313e61c8190b174b331365b803f |
completed | May 7, 2026, 5:59 p.m. |
| PD | Predicate disambiguation | batch_69fcd1f6b2e08190bf0300ae7c9ae67a |
completed | May 7, 2026, 5:55 p.m. |
Created at: May 3, 2026, 4:32 p.m.