Triple
T31798721
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Quatrième Cru Classé |
E811666
|
entity |
| Predicate | regionSide |
P51444
|
FINISHED |
| Object | Left Bank of Bordeaux |
—
|
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: Left Bank of Bordeaux | Statement: [Quatrième Cru Classé, regionSide, Left Bank of Bordeaux]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: regionSide Context triple: [Quatrième Cru Classé, regionSide, Left Bank of Bordeaux]
-
A.
regionCountrySide
Indicates that a region is located in or associated with the countryside or rural area of a country.
-
B.
provinceSide
Indicates that one entity is a side or bordering region of a province in relation to another entity.
-
C.
regionTypeOnOneSide
Indicates that one side of a boundary, object, or interface is associated with a specific type of region.
-
D.
region1
Indicates that one entity is the first or primary region associated with, containing, or encompassing another entity.
-
E.
locationSide
chosen
Indicates that one entity is positioned on a particular side (e.g., left, right, front, back) relative to another entity or reference point.
- 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_69f348e70d188190b4637c5509f81274 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69feabcda59481908f2bc13b46fcced1 |
completed | May 9, 2026, 3:36 a.m. |
| PD | Predicate disambiguation | batch_69feaabd63f88190b30dcf6dd2ea39d1 |
completed | May 9, 2026, 3:32 a.m. |
Created at: April 30, 2026, 11:41 p.m.