Triple
T26814282
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Romanée-Saint-Vivant |
E672081
|
entity |
| Predicate | appellationControl |
P161496
|
FINISHED |
| Object | AOC Romanée-Saint-Vivant |
—
|
NE NERFINISHED |
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: AOC Romanée-Saint-Vivant | Statement: [Romanée-Saint-Vivant, appellationControl, AOC Romanée-Saint-Vivant]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: appellationControl Context triple: [Romanée-Saint-Vivant, appellationControl, AOC Romanée-Saint-Vivant]
-
A.
appellationType
Indicates the specific kind or category of name or designation applied to an entity.
-
B.
includesAppellation
Indicates that one entity contains or incorporates another entity’s name, title, or designation as part of its own identification.
-
C.
appellationEnLangue
Indicates that an entity is designated by a specific appellation or name expressed in a given language.
-
D.
notableAppellation
Indicates that an entity is known by, or commonly referred to with, a particular notable name or title.
-
E.
appellationLevel
Indicates the hierarchical rank or degree of formality of a name, title, or designation assigned to an entity.
- 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_69eeb3225a3c8190aaf6746efeded2f3 |
completed | April 27, 2026, 12:51 a.m. |
| NER | Named-entity recognition | batch_69f61a83c8ec8190ba1f49371889e547 |
completed | May 2, 2026, 3:38 p.m. |
| PD | Predicate disambiguation | batch_69f611ad2eb48190ac1ed0090f13f7a9 |
completed | May 2, 2026, 3:01 p.m. |
| PDg | Predicate description generation | batch_69f6142a0b988190b404d078f73c3cb9 |
completed | May 2, 2026, 3:11 p.m. |
Created at: April 27, 2026, 4:31 a.m.