Triple
T7348714
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Seljuk art |
E169439
|
entity |
| Predicate | typicalMetalworkObject |
P26314
|
FINISHED |
| Object | basin |
—
|
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: basin | Statement: [Seljuk art, typicalMetalworkObject, basin]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalMetalworkObject Context triple: [Seljuk art, typicalMetalworkObject, basin]
-
A.
allMetalConstruction
Indicates that something is constructed entirely or almost entirely from metal components.
-
B.
associatedMetal
chosen
Indicates a relationship where one entity is linked or connected to a particular metal, such as by composition, usage, origin, or symbolic association.
-
C.
weaponForged
Indicates that one entity has been created or shaped as a weapon by another entity through a forging process.
-
D.
weaponForgedFor
Indicates that a weapon was specifically created or crafted for a particular entity, purpose, or context.
-
E.
stateMetal
Indicates that an entity is in a metallic state or exhibits properties characteristic of a metal.
- 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_69c68a5878888190968ce4d04db8d69f |
completed | March 27, 2026, 1:47 p.m. |
| NER | Named-entity recognition | batch_69c6f139505c8190a7158cf59a6e089e |
completed | March 27, 2026, 9:06 p.m. |
| PD | Predicate disambiguation | batch_69c6f02aeeb8819099d1626566cec18b |
completed | March 27, 2026, 9:01 p.m. |
Created at: March 27, 2026, 3:05 p.m.