Triple
T34815697
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Beaufort West, Cape Province, Union of South Africa |
E1003627
|
entity |
| Predicate | countryAtTimeOfBirthOfChristiaanBarnard |
P89959
|
FINISHED |
| Object | Union of 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: Union of South Africa | Statement: [Beaufort West, Cape Province, Union of South Africa, countryAtTimeOfBirthOfChristiaanBarnard, Union of South Africa]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: countryAtTimeOfBirthOfChristiaanBarnard Context triple: [Beaufort West, Cape Province, Union of South Africa, countryAtTimeOfBirthOfChristiaanBarnard, Union of South Africa]
-
A.
countryAtTheTime
Indicates that an entity is associated with a specific country as it existed at a particular point in time.
-
B.
countryOfEponym
Indicates that the related entity is named after something (an eponym) originating from or associated with a particular country.
-
C.
countryOfBirthAtTime
chosen
Indicates that an entity was born in a specified country, with the relationship qualified by a particular point or interval in time.
-
D.
creatorCountryOfBirth
Indicates the country where the creator of an entity was born.
-
E.
projectCountryAtTheTime
Indicates the country with which a project was associated at the specific time or period in question.
- 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_69f76db717088190811b4e744610f37d |
completed | May 3, 2026, 3:45 p.m. |
| NER | Named-entity recognition | batch_6a017d27e184819094638c3cf6876de4 |
completed | May 11, 2026, 6:54 a.m. |
| PD | Predicate disambiguation | batch_6a017c785a44819083111384b55769e9 |
completed | May 11, 2026, 6:51 a.m. |
Created at: May 3, 2026, 3:59 p.m.