Triple
T22158206
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hetian jade |
E547595
|
entity |
| Predicate | typicalCarvingMotifs |
P49005
|
FINISHED |
| Object | dragons |
—
|
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: dragons | Statement: [Hetian jade, typicalCarvingMotifs, dragons]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalCarvingMotifs Context triple: [Hetian jade, typicalCarvingMotifs, dragons]
-
A.
hasCarvings
Indicates that one entity features or contains carved designs or engravings on its surface, created by another entity or process.
-
B.
hasCarving
chosen
Indicates that one entity features or contains a carved design, inscription, or sculpted detail that is associated with or applied to another entity.
-
C.
hasFrontCarvings
Indicates that an object or structure features carvings or sculpted details on its front-facing surface.
-
D.
hasBranchCarvings
Indicates that an entity (such as a tree or wooden object) possesses carvings or engravings specifically on its branches.
-
E.
hasRootCarvings
Indicates that an object, typically a plant or tree, possesses carvings or engraved markings on its roots.
- 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_69e11e3b52088190ad5df386d01eb2fb |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f12a2aadb48190b4d739d1df9529db |
completed | April 28, 2026, 9:44 p.m. |
| PD | Predicate disambiguation | batch_69e71b41555881909b8e22718974d527 |
completed | April 21, 2026, 6:37 a.m. |
Created at: April 16, 2026, 8:33 p.m.