Triple
T8352871
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zsolnay porcelain |
E196603
|
entity |
| Predicate | glazeProperty |
P67678
|
FINISHED |
| Object | iridescent finish |
—
|
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: iridescent finish | Statement: [Zsolnay porcelain, glazeProperty, iridescent finish]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: glazeProperty Context triple: [Zsolnay porcelain, glazeProperty, iridescent finish]
-
A.
glaze
chosen
Indicates that an agent coats or covers a surface of an entity with a smooth, often shiny or protective, layer or substance.
-
B.
glazingType
Indicates the type or configuration of glazing (such as single, double, or special coatings) used in or applied to an element.
-
C.
resinProperty
Indicates that a resin possesses or is characterized by a specific property or attribute.
-
D.
angleProperty
Indicates that a relationship specifies a particular geometric or quantitative characteristic (such as measure, type, or orientation) of an angle between entities.
-
E.
scalingProperty
Indicates how a quantity or behavior changes in proportion to changes in another variable, typically under resizing or rescaling conditions.
- 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_69ca82f08b348190bfb7881944bbff6f |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cb80460f048190aa298ddffde1047d |
completed | March 31, 2026, 8:05 a.m. |
| PD | Predicate disambiguation | batch_69cb70c6d0ec8190acf273b0e007b51a |
completed | March 31, 2026, 6:59 a.m. |
Created at: March 30, 2026, 5:59 p.m.