Triple
T2381734
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Saumur-Champigny |
E46324
|
entity |
| Predicate | styleComparison |
P19247
|
FINISHED |
| Object | often lighter than Bordeaux Cabernet Franc wines |
—
|
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: often lighter than Bordeaux Cabernet Franc wines | Statement: [Saumur-Champigny, styleComparison, often lighter than Bordeaux Cabernet Franc wines]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: styleComparison Context triple: [Saumur-Champigny, styleComparison, often lighter than Bordeaux Cabernet Franc wines]
-
A.
styleTendsTo
chosen
Indicates that one style is generally inclined or likely to develop, appear, or be adopted in the direction of another style.
-
B.
scaleComparison
Indicates a relationship where two or more entities are compared in terms of their size, magnitude, or scale relative to one another.
-
C.
styleInFull
Indicates that something is presented, written, or expressed in its complete, unabbreviated, or fully detailed form.
-
D.
stylePeriod
Indicates the stylistic or historical period with which an entity (such as an artwork, artifact, or performance) is associated.
-
E.
relatedStyle
Indicates that one style is associated with, similar to, or derived from another style in some relevant way.
- 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_69a88a1554a48190a0180682bcf099be |
completed | March 4, 2026, 7:37 p.m. |
| NER | Named-entity recognition | batch_69abc7b98c988190abdb4fe51bf65bde |
completed | March 7, 2026, 6:37 a.m. |
| PD | Predicate disambiguation | batch_69abc59f73f08190924a36d7d475d8f4 |
completed | March 7, 2026, 6:28 a.m. |
Created at: March 4, 2026, 7:57 p.m.