Triple
T9928044
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tuks |
E187971
|
entity |
| Predicate | usedAsBrand |
P12411
|
FINISHED |
| Object | University of Pretoria sport brand |
—
|
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: University of Pretoria sport brand | Statement: [Tuks, usedAsBrand, University of Pretoria sport brand]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usedAsBrand Context triple: [Tuks, usedAsBrand, University of Pretoria sport brand]
-
A.
usedBrand
Indicates that an entity has utilized, applied, or operated a particular brand in some context.
-
B.
usedBrandOf
Indicates that one entity made use of or operated an item, product, or service associated with a particular brand.
-
C.
usedInBrand
chosen
Indicates that something (such as a component, material, or element) is utilized as part of or within a particular brand.
-
D.
usesBrandCharacter
Indicates that one entity employs or features another entity’s brand character (such as a mascot or branded persona) in its materials, products, or communications.
-
E.
usedBrandOnScreenUntil
Indicates that a particular brand continued to be shown or featured on screen up to a specified time or event.
- 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_69ca82b22a688190b52c75bd48429c10 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cdb59d7ad08190982a1584547190bd |
completed | April 2, 2026, 12:17 a.m. |
| PD | Predicate disambiguation | batch_69cd1d90b8a8819081748f129c0c6ab6 |
completed | April 1, 2026, 1:28 p.m. |
Created at: March 30, 2026, 8:43 p.m.