Triple
T10195108
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | District 9 |
E238141
|
entity |
| Predicate | character |
P662
|
FINISHED |
| Object | Wikus van de Merwe |
E769156
|
NE 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: Wikus van de Merwe | Statement: [District 9, character, Wikus van de Merwe]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Wikus van de Merwe Context triple: [District 9, character, Wikus van de Merwe]
-
A.
Wikus van de Merwe
chosen
Wikus van de Merwe is the bumbling South African bureaucrat who becomes the reluctant, transforming protagonist at the center of the sci-fi film "District 9."
-
B.
Andries Treurnicht
Andries Treurnicht was a prominent South African politician and staunch defender of apartheid who led a right-wing breakaway from the ruling National Party.
-
C.
Dirkie Uys
Dirkie Uys was a young Voortrekker hero of South African history, remembered for his bravery and death alongside his father during conflicts with the Zulu in the 1830s.
-
D.
Hendrik van der Bijl
Hendrik van der Bijl was a prominent South African electrical engineer and industrialist who played a key role in developing the country’s power and steel industries.
-
E.
Adriaan Louw
Adriaan Louw is a South African-born physical therapist and pain scientist known for his work on pain neuroscience education and chronic pain management.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69ca84de1b208190bf17bb305b002605 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cdedc7cc748190bceb8f657afcc054 |
completed | April 2, 2026, 4:17 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d6a7d465bc8190b419de253616b0fd |
completed | April 8, 2026, 7:09 p.m. |
Created at: March 30, 2026, 9:13 p.m.