Triple
T23364215
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | State Capture Inquiry |
E593266
|
entity |
| Predicate | investigated |
P6157
|
FINISHED |
| Object |
Bosasa
Bosasa was a controversial South African facilities management company widely implicated in large-scale corruption and bribery involving government officials.
|
E1583081
|
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: Bosasa | Statement: [State Capture Inquiry, investigated, Bosasa]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bosasa Context triple: [State Capture Inquiry, investigated, Bosasa]
-
A.
Bruno Putzulu
Bruno Putzulu is a French actor known for his work in auteur cinema, particularly in films by directors like Jean-Luc Godard.
-
B.
Assin Foso
Assin Foso is a prominent town in Ghana that serves as a commercial and administrative hub within the country’s Central Region.
-
C.
Deuba
Deuba is a coastal village located in Serua Province on the island of Viti Levu in Fiji.
-
D.
Dadoo
Dadoo is the surname of Yusuf Dadoo, a prominent South African anti-apartheid activist and political leader.
-
E.
Mialisa Bonta
Mialisa Bonta is an American politician and attorney who serves in the California State Assembly, representing parts of the East Bay.
- 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: Bosasa Triple: [State Capture Inquiry, investigated, Bosasa]
Generated description
Bosasa was a controversial South African facilities management company widely implicated in large-scale corruption and bribery involving government officials.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Bosasa Target entity description: Bosasa was a controversial South African facilities management company widely implicated in large-scale corruption and bribery involving government officials.
-
A.
Bruno Putzulu
Bruno Putzulu is a French actor known for his work in auteur cinema, particularly in films by directors like Jean-Luc Godard.
-
B.
Assin Foso
Assin Foso is a prominent town in Ghana that serves as a commercial and administrative hub within the country’s Central Region.
-
C.
Deuba
Deuba is a coastal village located in Serua Province on the island of Viti Levu in Fiji.
-
D.
Dadoo
Dadoo is the surname of Yusuf Dadoo, a prominent South African anti-apartheid activist and political leader.
-
E.
Mialisa Bonta
Mialisa Bonta is an American politician and attorney who serves in the California State Assembly, representing parts of the East Bay.
- 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_69e25d2593c88190bcdf4a716a94ccb2 |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f1a0aac4248190a4663ed12aed6856 |
completed | April 29, 2026, 6:09 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0c5dd78f508190b3b83e4cc2625163 |
completed | May 19, 2026, 12:55 p.m. |
| NEDg | Description generation | batch_6a0c60473de0819096d3b4e35da16295 |
completed | May 19, 2026, 1:06 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0c60b52fe88190854803902df750c5 |
completed | May 19, 2026, 1:08 p.m. |
Created at: April 17, 2026, 5:31 p.m.