Triple
T2658271
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Blood Diamond |
E54665
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object |
Kagiso Kuypers
Kagiso Kuypers is an actor best known for his role in the 2006 political war thriller film "Blood Diamond."
|
E304169
|
NE FINISHED |
How this triple was built (4 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: Kagiso Kuypers | Statement: [Blood Diamond, starring, Kagiso Kuypers]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kagiso Kuypers Context triple: [Blood Diamond, starring, Kagiso Kuypers]
-
A.
Behati Prinsloo
Behati Prinsloo is a Namibian model best known for her long-running work with Victoria’s Secret and for being one of the brand’s prominent Angels.
-
B.
Jopie Fourie
Jopie Fourie was a South African Boer rebel and national figure executed during World War I for leading an armed uprising against the Union government.
-
C.
Danie Louw
Danie Louw is a notable individual recognized for achievements significant enough to be associated with the surname Louw.
-
D.
Elize Botha
Elize Botha was the wife of former South African State President P. W. Botha and served as the country’s First Lady during his tenure.
-
E.
Bridgette Radebe
Bridgette Radebe is a South African mining entrepreneur and businesswoman, recognized as one of the country’s first black female mine owners and a prominent figure in the mining industry.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Kagiso Kuypers Triple: [Blood Diamond, starring, Kagiso Kuypers]
Generated description
Kagiso Kuypers is an actor best known for his role in the 2006 political war thriller film "Blood Diamond."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Kagiso Kuypers Target entity description: Kagiso Kuypers is an actor best known for his role in the 2006 political war thriller film "Blood Diamond."
-
A.
Behati Prinsloo
Behati Prinsloo is a Namibian model best known for her long-running work with Victoria’s Secret and for being one of the brand’s prominent Angels.
-
B.
Jopie Fourie
Jopie Fourie was a South African Boer rebel and national figure executed during World War I for leading an armed uprising against the Union government.
-
C.
Danie Louw
Danie Louw is a notable individual recognized for achievements significant enough to be associated with the surname Louw.
-
D.
Elize Botha
Elize Botha was the wife of former South African State President P. W. Botha and served as the country’s First Lady during his tenure.
-
E.
Bridgette Radebe
Bridgette Radebe is a South African mining entrepreneur and businesswoman, recognized as one of the country’s first black female mine owners and a prominent figure in the mining industry.
- F. None of above. chosen
Provenance (5 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_69ab49e028948190b97e01d73548b1d9 |
completed | March 6, 2026, 9:40 p.m. |
| NER | Named-entity recognition | batch_69abd94dcaa48190aec625f68ce61a02 |
completed | March 7, 2026, 7:52 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69afe88d510c81908cdd3337e0eaca2c |
completed | March 10, 2026, 9:46 a.m. |
| NEDg | Description generation | batch_69afe9d87eac8190a9373abab608f088 |
completed | March 10, 2026, 9:52 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69b00dff7bcc81909b578e7209850b17 |
completed | March 10, 2026, 12:26 p.m. |
Created at: March 6, 2026, 9:53 p.m.