Triple
T21284214
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Maputo Province |
E524609
|
entity |
| Predicate | borderDirectionToCountry |
P27801
|
FINISHED |
| Object | South Africa to the west |
—
|
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: South Africa to the west | Statement: [Maputo Province, borderDirectionToCountry, South Africa to the west]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: borderDirectionToCountry Context triple: [Maputo Province, borderDirectionToCountry, South Africa to the west]
-
A.
countryBorderDirection
chosen
Indicates the cardinal or relative direction in which one country lies in relation to the border it shares with another country.
-
B.
borderDirectionFromUS
Indicates the compass direction in which a country or region lies relative to the United States along their shared border.
-
C.
borderCountrySide
Indicates that one country shares a land border with the side or region of another country.
-
D.
borderDirectionFromCapital
Indicates the compass direction from a country's capital city to a specified border or neighboring entity.
-
E.
hasBorderTerminusCountry
Indicates that a country serves as the endpoint or boundary limit of a border segment associated with 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_69e0b5171f6c8190a5d57201ede73811 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e736d4e7f881909c2cc7936a66b79d |
completed | April 21, 2026, 8:35 a.m. |
| PD | Predicate disambiguation | batch_69e61612ab748190a72b8703b938abcb |
completed | April 20, 2026, 12:03 p.m. |
Created at: April 16, 2026, 4:03 p.m.