Triple
T23149924
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tamba ware |
E578294
|
entity |
| Predicate | typicalGlaze |
P37912
|
FINISHED |
| Object | natural ash glaze |
—
|
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: natural ash glaze | Statement: [Tamba ware, typicalGlaze, natural ash glaze]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalGlaze Context triple: [Tamba ware, typicalGlaze, natural ash glaze]
-
A.
glaze
Indicates that an agent coats or covers a surface of an entity with a smooth, often shiny or protective, layer or substance.
-
B.
typicalFrosting
Indicates that something is the standard or commonly used type of frosting associated with a particular item or context.
-
C.
typicalFinish
Indicates that an action, process, or event commonly or characteristically ends with a particular outcome or state.
-
D.
glazingType
chosen
Indicates the type or configuration of glazing (such as single, double, or special coatings) used in or applied to an element.
-
E.
glazingPattern
Indicates the arrangement or design pattern of glazing elements (such as panes or glass sections) within a structure or object.
- 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_69e245fb8de081908f0eba7b5fd75bc4 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f18ed0b76c8190ac61b949d88e9970 |
completed | April 29, 2026, 4:53 a.m. |
| PD | Predicate disambiguation | batch_69ef89f83b108190aaaa1db6221fc163 |
completed | April 27, 2026, 4:08 p.m. |
Created at: April 17, 2026, 4:01 p.m.