Triple
T2236992
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sémillon |
E49304
|
entity |
| Predicate | primaryRoleIn |
P30063
|
FINISHED |
| Object | sweet wines of Sauternes |
—
|
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: sweet wines of Sauternes | Statement: [Sémillon, primaryRoleIn, sweet wines of Sauternes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primaryRoleIn Context triple: [Sémillon, primaryRoleIn, sweet wines of Sauternes]
-
A.
primaryPosition
Indicates the main role, job, or position an entity holds among potentially multiple positions.
-
B.
laterPrimaryRole
Indicates that an entity assumes a specified primary role at a later time than another role or state in a sequence.
-
C.
primaryArea
Indicates that one entity is the main or most important area, domain, or field associated with another entity.
-
D.
primaryMode
Indicates the main or most commonly used method, manner, or form in which an action, process, or interaction is carried out between entities.
-
E.
primaryActor
chosen
Indicates that the referenced entity is the main participant or most central party responsible for the action or event in the relationship.
- 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_69a88aa84bdc819086df50e9c20b301e |
completed | March 4, 2026, 7:40 p.m. |
| NER | Named-entity recognition | batch_69abc09573848190bf91eddcc2fa0061 |
completed | March 7, 2026, 6:07 a.m. |
| PD | Predicate disambiguation | batch_69abbdafc07881909101266a33ae7031 |
completed | March 7, 2026, 5:54 a.m. |
Created at: March 4, 2026, 7:47 p.m.