Triple
T22254624
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Prince Dabulamanzi kaMpande |
E550065
|
entity |
| Predicate | placeOfActivity |
P1527
|
FINISHED |
| Object |
Gingindlovu
Gingindlovu is a town in KwaZulu-Natal, South Africa, historically associated with Zulu military activity and the Anglo-Zulu War.
|
E1527721
|
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: Gingindlovu | Statement: [Prince Dabulamanzi kaMpande, placeOfActivity, Gingindlovu]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gingindlovu Context triple: [Prince Dabulamanzi kaMpande, placeOfActivity, Gingindlovu]
-
A.
Zvongombe
Zvongombe was the principal urban and political center of the Mutapa Kingdom in what is now northern Zimbabwe.
-
B.
Vindza
Vindza is a small town located within the Pool Department of the Republic of the Congo.
-
C.
Gatenga
Gatenga is an urban sector within Kigali, Rwanda, known for its residential neighborhoods and local commercial activity.
-
D.
Ilanga
Ilanga is a South African newspaper, historically significant as one of the country’s oldest isiZulu-language publications.
-
E.
Zangezi
Zangezi is an experimental poetic drama by Russian Futurist writer Velimir Khlebnikov, known for its inventive language and visionary, prophetic themes.
- 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: Gingindlovu Triple: [Prince Dabulamanzi kaMpande, placeOfActivity, Gingindlovu]
Generated description
Gingindlovu is a town in KwaZulu-Natal, South Africa, historically associated with Zulu military activity and the Anglo-Zulu War.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Gingindlovu Target entity description: Gingindlovu is a town in KwaZulu-Natal, South Africa, historically associated with Zulu military activity and the Anglo-Zulu War.
-
A.
Zvongombe
Zvongombe was the principal urban and political center of the Mutapa Kingdom in what is now northern Zimbabwe.
-
B.
Vindza
Vindza is a small town located within the Pool Department of the Republic of the Congo.
-
C.
Gatenga
Gatenga is an urban sector within Kigali, Rwanda, known for its residential neighborhoods and local commercial activity.
-
D.
Ilanga
Ilanga is a South African newspaper, historically significant as one of the country’s oldest isiZulu-language publications.
-
E.
Zangezi
Zangezi is an experimental poetic drama by Russian Futurist writer Velimir Khlebnikov, known for its inventive language and visionary, prophetic themes.
- 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_69e11e42adb8819087714772ea606709 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f138c1d70881908df47b0f818c0022 |
completed | April 28, 2026, 10:46 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0ab662334c819095b6737e550bd5ce |
completed | May 18, 2026, 6:49 a.m. |
| NEDg | Description generation | batch_6a0ab77252b0819098e9daa2930ceb6a |
completed | May 18, 2026, 6:53 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0ab81e47a08190b4148080f363fcf5 |
completed | May 18, 2026, 6:56 a.m. |
Created at: April 16, 2026, 8:39 p.m.