Triple
T37260359
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | South Africa–Argentina relations |
E924240
|
entity |
| Predicate | ArgentineEmbassyLocationCity |
P187352
|
FINISHED |
| Object | Pretoria |
—
|
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: Pretoria | Statement: [South Africa–Argentina relations, ArgentineEmbassyLocationCity, Pretoria]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ArgentineEmbassyLocationCity Context triple: [South Africa–Argentina relations, ArgentineEmbassyLocationCity, Pretoria]
-
A.
majorCityOnArgentineSide
Indicates that the referenced city is a principal or major urban center located on the Argentine side of a border, region, or shared geographic feature.
-
B.
countryCityArgentina
Indicates a relationship where a city is located within the country of Argentina.
-
C.
nearCityInArgentina
Indicates that one entity is located close to, but not necessarily within, a specified city in Argentina.
-
D.
distanceFromBuenosAires
Indicates the measured distance between a given entity’s location and the city of Buenos Aires.
-
E.
directionFromBuenosAires
Indicates the cardinal or relative compass direction of an entity as measured from Buenos Aires.
- 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_69f76eabd6c481909d414a80a1345c98 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fb4134225081909fd60703b8cae397 |
completed | May 6, 2026, 1:25 p.m. |
| PD | Predicate disambiguation | batch_69fb35bf767081908de8345358ca7f44 |
completed | May 6, 2026, 12:36 p.m. |
| PDg | Predicate description generation | batch_69fb41333b548190912cb238ffc271c9 |
completed | May 6, 2026, 1:25 p.m. |
Created at: May 3, 2026, 4:15 p.m.