Triple
T26949906
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Haeinsa |
E678751
|
entity |
| Predicate | ThreeJewelAspect |
P64550
|
FINISHED |
| Object | Dharma (Buddha’s teachings) |
—
|
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: Dharma (Buddha’s teachings) | Statement: [Haeinsa, ThreeJewelAspect, Dharma (Buddha’s teachings)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ThreeJewelAspect Context triple: [Haeinsa, ThreeJewelAspect, Dharma (Buddha’s teachings)]
-
A.
givesJewelsTo
Indicates that one entity transfers or presents jewels to another entity.
-
B.
relationshipWithJewel
Indicates that one entity has a specified type of relationship or association with a jewel or jewelry item.
-
C.
symbolicAspect
chosen
Indicates that one entity functions as a symbol or emblem that represents, expresses, or conveys a particular meaning, quality, or concept of another entity.
-
D.
associatedWithSymbolStones
Indicates a relationship where something is connected or linked to symbol stones, such as being found with them, derived from them, or contextually related to them.
-
E.
numberOfDecorativeJewels
Indicates the count of decorative jewels associated with or present on a given entity.
- 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_69eeeb4e75f08190b14fc91ca4a91488 |
completed | April 27, 2026, 4:51 a.m. |
| NER | Named-entity recognition | batch_69f6208934108190b9ae04c0ed2c4dde |
completed | May 2, 2026, 4:04 p.m. |
| PD | Predicate disambiguation | batch_69f611af72ac819094598dd2530d7411 |
completed | May 2, 2026, 3:01 p.m. |
Created at: April 27, 2026, 6:24 a.m.