Triple
T24346138
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pierre de Villiers |
E613644
|
entity |
| Predicate | hasSportCountry |
P4833
|
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: [Pierre de Villiers, hasSportCountry, South Africa]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSportCountry Context triple: [Pierre de Villiers, hasSportCountry, South Africa]
-
A.
sportCountry
chosen
Indicates the country with which a given sport, sporting event, or sports organization is associated or primarily linked.
-
B.
hasNationalSportTeam
Indicates that an entity possesses or is represented by an official national-level sports team.
-
C.
laterSportCountry
Indicates that one country’s involvement in a sport occurs at a later time than another country’s involvement in that same sport.
-
D.
usedForSportsCountryCodes
Indicates that the referenced country codes are those used specifically for identifying countries in sports contexts or competitions.
-
E.
sportCountryCombination
Indicates a relationship pairing a specific sport with a specific country, typically to represent where that sport is played, represented, or associated.
- 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_69e2d7ddd29481909e7f539a6072bd71 |
completed | April 18, 2026, 1:01 a.m. |
| NER | Named-entity recognition | batch_69f2932978b88190afc441a3d4805e5f |
completed | April 29, 2026, 11:24 p.m. |
| PD | Predicate disambiguation | batch_69f287ad30048190b3ad3613486f277f |
completed | April 29, 2026, 10:35 p.m. |
Created at: April 18, 2026, 1:58 a.m.