Triple
T25895772
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tongdosa |
E652464
|
entity |
| Predicate | representsInThreeJewels |
P72867
|
FINISHED |
| Object | Buddha (Sakyamuni) |
—
|
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: Buddha (Sakyamuni) | Statement: [Tongdosa, representsInThreeJewels, Buddha (Sakyamuni)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: representsInThreeJewels Context triple: [Tongdosa, representsInThreeJewels, Buddha (Sakyamuni)]
-
A.
componentRepresents
Indicates that one component stands in for, symbolizes, or models another entity or concept within a system or context.
-
B.
representsInRelationsWith
Indicates that an entity serves as a representative or proxy for another entity within a specified relationship or set of relationships.
-
C.
givesProductRepresentationOf
Indicates that one entity provides or expresses another entity in the form of a product representation, such as a model, depiction, or structured description of that product.
-
D.
representsAs
chosen
Indicates that one entity serves as a depiction, symbol, or stand-in for another entity in some representational context.
-
E.
representedInPartBy
Indicates that something is partially depicted, expressed, or captured within another thing, but not in its entirety.
- 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_69e7ab3c6cc081908de59bfcc28ec19d |
completed | April 21, 2026, 4:52 p.m. |
| NER | Named-entity recognition | batch_69f6d0d46aec819091edf97324d793ac |
completed | May 3, 2026, 4:36 a.m. |
| PD | Predicate disambiguation | batch_69f6cfe2183481908ae4e85a59c66f69 |
completed | May 3, 2026, 4:32 a.m. |
Created at: April 22, 2026, 8:23 a.m.