Triple
T1871326
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kanuri |
E39040
|
entity |
| Predicate | historicalCapital |
P2536
|
FINISHED |
| Object |
Ngazargamu
Ngazargamu was the principal capital city of the Kanem-Bornu Empire in the Lake Chad region, serving as a major political and commercial center in precolonial West Africa.
|
E212833
|
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: Ngazargamu | Statement: [Kanuri, historicalCapital, Ngazargamu]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ngazargamu Context triple: [Kanuri, historicalCapital, Ngazargamu]
-
A.
Gardabani
Gardabani is a town in southeastern Georgia known for its role as an industrial and energy hub within the Kvemo Kartli region.
-
B.
Kadamtala
Kadamtala is a small settlement located on Middle Andaman Island in the Andaman and Nicobar Islands of India.
-
C.
Dangamvura
Dangamvura is a residential suburb of Mutare, a major city in eastern Zimbabwe.
-
D.
Lagodekhi
Lagodekhi is a town in eastern Georgia known as a regional center near the Azerbaijani border and as the gateway to the Lagodekhi Protected Areas in the Kakheti region.
-
E.
Gwarinpa
Gwarinpa is a large, planned residential district in Abuja, Nigeria, known for its extensive housing estates and relatively well-organized urban layout.
- 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: Ngazargamu Triple: [Kanuri, historicalCapital, Ngazargamu]
Generated description
Ngazargamu was the principal capital city of the Kanem-Bornu Empire in the Lake Chad region, serving as a major political and commercial center in precolonial West Africa.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Ngazargamu Target entity description: Ngazargamu was the principal capital city of the Kanem-Bornu Empire in the Lake Chad region, serving as a major political and commercial center in precolonial West Africa.
-
A.
Gardabani
Gardabani is a town in southeastern Georgia known for its role as an industrial and energy hub within the Kvemo Kartli region.
-
B.
Kadamtala
Kadamtala is a small settlement located on Middle Andaman Island in the Andaman and Nicobar Islands of India.
-
C.
Dangamvura
Dangamvura is a residential suburb of Mutare, a major city in eastern Zimbabwe.
-
D.
Lagodekhi
Lagodekhi is a town in eastern Georgia known as a regional center near the Azerbaijani border and as the gateway to the Lagodekhi Protected Areas in the Kakheti region.
-
E.
Gwarinpa
Gwarinpa is a large, planned residential district in Abuja, Nigeria, known for its extensive housing estates and relatively well-organized urban layout.
- 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_69a8862f7074819096afe7fe65e179e9 |
completed | March 4, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69abb0ba90e08190b990875d6e8e7e4a |
completed | March 7, 2026, 4:59 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69adeae228008190a0d427c74fd37511 |
completed | March 8, 2026, 9:32 p.m. |
| NEDg | Description generation | batch_69adebd146408190b80a7d8e8974a90d |
completed | March 8, 2026, 9:36 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69adec551c688190a0bcdc16ab6e3ecc |
completed | March 8, 2026, 9:38 p.m. |
Created at: March 4, 2026, 7:34 p.m.