Triple
T9299789
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tâmega River |
E223728
|
entity |
| Predicate | formsBorder |
P43209
|
FINISHED |
| Object | sections of the Portugal–Spain border |
—
|
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: sections of the Portugal–Spain border | Statement: [Tâmega River, formsBorder, sections of the Portugal–Spain border]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: formsBorder Context triple: [Tâmega River, formsBorder, sections of the Portugal–Spain border]
-
A.
borderColor
Indicates the color that forms the boundary or outline of an entity.
-
B.
recognizedBorder
Indicates that one entity formally acknowledges and accepts another entity’s boundary as a legitimate border.
-
C.
sharesBorderType
Indicates that two entities are connected by a common boundary characterized by the same specified type of border (e.g., land, river, maritime).
-
D.
relatedBorder
chosen
Indicates that two geographic or political entities share a common boundary or border with each other.
-
E.
borderText
Indicates that one entity is the textual content displayed along the border 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_69ca8423edb08190bc0c91287a484768 |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cd08d070c881908bed41aada6f85ae |
completed | April 1, 2026, noon |
| PD | Predicate disambiguation | batch_69cc7a5ef1908190bc5ca166bb895af6 |
completed | April 1, 2026, 1:52 a.m. |
Created at: March 30, 2026, 7:36 p.m.