Triple
T8440226
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ga-Rankuwa Campus |
E199332
|
entity |
| Predicate | locatedIn |
P40
|
FINISHED |
| Object | Ga-Rankuwa |
E191907
|
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: Ga-Rankuwa | Statement: [Ga-Rankuwa Campus, locatedIn, Ga-Rankuwa]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ga-Rankuwa Context triple: [Ga-Rankuwa Campus, locatedIn, Ga-Rankuwa]
-
A.
Ga-Rankuwa
chosen
Ga-Rankuwa is a township in the northern part of Gauteng, South Africa, known for its residential communities and proximity to major industrial and educational hubs near Pretoria.
-
B.
Rumuibekwe
Rumuibekwe is a prominent residential and commercial town within Obio-Akpor Local Government Area in Rivers State, Nigeria.
-
C.
Raklungu
Raklungu is an indigenous local language spoken on Atauro Island, near Timor-Leste.
-
D.
Urambo
Urambo is a town and district headquarters in western Tanzania known historically for tobacco production and its location within the Tabora Region.
-
E.
Zangaléwa
Zangaléwa is a popular 1986 makossa song by the Cameroonian group Golden Sounds, widely known across Africa and later internationally after being adapted into Shakira’s World Cup anthem "Waka Waka (This Time for Africa)."
- 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_69ca8314cd6c8190a6b8c2a1096e18f3 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbe13708988190a534e38d8254c9bd |
completed | March 31, 2026, 2:59 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ce1d9140b48190ad0c493948a3de5e |
completed | April 2, 2026, 7:41 a.m. |
Created at: March 30, 2026, 6:08 p.m.