Triple
T12385481
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mourvèdre |
E295850
|
entity |
| Predicate | notableBlendStyle |
P104683
|
FINISHED |
| Object | GSM blend |
—
|
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: GSM blend | Statement: [Mourvèdre, notableBlendStyle, GSM blend]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: notableBlendStyle Context triple: [Mourvèdre, notableBlendStyle, GSM blend]
-
A.
typicalBlendStyle
Indicates the usual or characteristic way in which two or more elements are combined or mixed together.
-
B.
notableStyleFeature
Indicates that an entity possesses a distinctive stylistic characteristic or design element that is especially noteworthy or defining.
-
C.
hasBlendOfOldAndNew
Indicates that something combines or integrates both traditional/older elements and modern/newer elements into a single whole.
-
D.
transparencyEffects
Indicates how the level or presence of transparency in one entity influences the perception, behavior, or properties of another entity.
-
E.
notableSubstyle
Indicates that one style is a notable or distinct subcategory within another broader style.
- F. None of above. chosen
Provenance (4 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_69d6ad9e653c8190b1473c860ee53dae |
completed | April 8, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69d93fbd489c819098233a111442762e |
completed | April 10, 2026, 6:21 p.m. |
| PD | Predicate disambiguation | batch_69d93ed256788190b704cad171a4824e |
completed | April 10, 2026, 6:17 p.m. |
| PDg | Predicate description generation | batch_69d93fa244148190a960be3ff6f1cf45 |
completed | April 10, 2026, 6:21 p.m. |
Created at: April 8, 2026, 9:54 p.m.