Triple
T26999438
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gold Fields Limited |
E680064
|
entity |
| Predicate | hasOperationInCountry |
P20059
|
FINISHED |
| Object | South Africa |
—
|
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: South Africa | Statement: [Gold Fields Limited, hasOperationInCountry, South Africa]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasOperationInCountry Context triple: [Gold Fields Limited, hasOperationInCountry, South Africa]
-
A.
operatesInCountries
chosen
Indicates that an entity conducts its activities or business within the specified countries.
-
B.
hasComponentInCountry
Indicates that an entity has a component, part, or sub-unit that is located in a specified country.
-
C.
operatesFacilityInCountry
Indicates that an entity runs or manages a facility that is located within a specified country.
-
D.
operatesToRegion
Indicates that an agent conducts operations or provides services directed toward or within a specified region.
-
E.
isSetInCountry
Indicates that something (such as an event, story, or scene) takes place within the geographical or political boundaries of a specified country.
- 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_69eeeb52908c8190bd246244686aa455 |
completed | April 27, 2026, 4:51 a.m. |
| NER | Named-entity recognition | batch_69f69edbb7648190bd89c57e0932eac1 |
completed | May 3, 2026, 1:03 a.m. |
| PD | Predicate disambiguation | batch_69f69d17e8d48190b30bcc2f4bd81eb2 |
completed | May 3, 2026, 12:55 a.m. |
Created at: April 27, 2026, 6:56 a.m.