Triple
T8946736
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bordeaux–Toulouse–Marseille |
E213238
|
entity |
| Predicate | westernTerminusDescription |
P13603
|
FINISHED |
| Object | Atlantic city of Bordeaux |
—
|
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: Atlantic city of Bordeaux | Statement: [Bordeaux–Toulouse–Marseille, westernTerminusDescription, Atlantic city of Bordeaux]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: westernTerminusDescription Context triple: [Bordeaux–Toulouse–Marseille, westernTerminusDescription, Atlantic city of Bordeaux]
-
A.
westernTerminusDetail
chosen
Indicates the specific endpoint location or characteristics associated with the western terminus of a route or linear feature.
-
B.
westernTerminusNear
Indicates that the western endpoint of one entity is located close to another entity.
-
C.
westernTerminusState
Indicates the state in which something (such as a route, line, or path) has its western endpoint or terminus.
-
D.
westernTerminusCountry
Indicates the country in which the westernmost endpoint of something (such as a route, line, or feature) is located.
-
E.
locatedWestOf
Indicates that one entity is positioned geographically to the west of another entity.
- 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_69ca839843408190a39069a029a89f15 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc66dd00c481908ff20fd66c1954cc |
completed | April 1, 2026, 12:29 a.m. |
| PD | Predicate disambiguation | batch_69cc5ed5267c8190a43feb2a2f3df1ec |
completed | March 31, 2026, 11:55 p.m. |
Created at: March 30, 2026, 6:59 p.m.