Triple
T7090727
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Delftware ceramics |
E165186
|
entity |
| Predicate | usedPigment |
P1272
|
FINISHED |
| Object | cobalt oxide |
—
|
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: cobalt oxide | Statement: [Delftware ceramics, usedPigment, cobalt oxide]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usedPigment Context triple: [Delftware ceramics, usedPigment, cobalt oxide]
-
A.
usesDyes
Indicates that one entity employs or applies dyes in relation to another entity or process.
-
B.
secondaryPigment
Indicates that one pigment functions as a secondary or supporting color relative to another primary pigment in a given context.
-
C.
usedInBlends
Indicates that something serves as an ingredient or component within one or more mixtures, combinations, or blends.
-
D.
materialUsed
chosen
Indicates that one entity is made from, incorporates, or utilizes the other entity as its material or substance.
-
E.
usedParticle
Indicates that one entity employs or applies a particular particle (e.g., subatomic, linguistic, or material) in some process, context, or construction involving another 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_69c6887e8c10819091cee237560d32da |
completed | March 27, 2026, 1:39 p.m. |
| NER | Named-entity recognition | batch_69c6e53012b081908bf40541d85c82f1 |
completed | March 27, 2026, 8:14 p.m. |
| PD | Predicate disambiguation | batch_69c6e1c172148190bf290c07bf579d1f |
completed | March 27, 2026, 8 p.m. |
Created at: March 27, 2026, 2:41 p.m.