Triple
T9167064
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ségou |
E219985
|
entity |
| Predicate | historicalRuler |
P3022
|
FINISHED |
| Object |
Ngolo Diarra
Ngolo Diarra was an 18th-century ruler who transformed Ségou into a powerful Bambara kingdom in the region of present-day Mali.
|
E784112
|
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: Ngolo Diarra | Statement: [Ségou, historicalRuler, Ngolo Diarra]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ngolo Diarra Context triple: [Ségou, historicalRuler, Ngolo Diarra]
-
A.
Ndiadiane Ndiaye
Ndiadiane Ndiaye is traditionally regarded as the legendary founder and first ruler of the Jolof (Wolof) Empire in what is now Senegal.
-
B.
Kalidou
Kalidou is a masculine given name most notably borne by Senegalese professional footballer Kalidou Koulibaly.
-
C.
Yaya Touré
Yaya Touré is a retired Ivorian midfielder renowned for his dominant box-to-box play and key role in Manchester City's rise to Premier League prominence.
-
D.
Hamed Bakayoko
Hamed Bakayoko was an Ivorian politician who served as Prime Minister and was a key figure in Côte d'Ivoire's post-conflict political landscape.
-
E.
Solomana Kante
Solomana Kanté was a Guinean scholar and linguist best known for inventing the N’Ko script to write Manding languages and promote literacy and cultural identity in West Africa.
- 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: Ngolo Diarra Triple: [Ségou, historicalRuler, Ngolo Diarra]
Generated description
Ngolo Diarra was an 18th-century ruler who transformed Ségou into a powerful Bambara kingdom in the region of present-day Mali.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Ngolo Diarra Target entity description: Ngolo Diarra was an 18th-century ruler who transformed Ségou into a powerful Bambara kingdom in the region of present-day Mali.
-
A.
Ndiadiane Ndiaye
Ndiadiane Ndiaye is traditionally regarded as the legendary founder and first ruler of the Jolof (Wolof) Empire in what is now Senegal.
-
B.
Kalidou
Kalidou is a masculine given name most notably borne by Senegalese professional footballer Kalidou Koulibaly.
-
C.
Yaya Touré
Yaya Touré is a retired Ivorian midfielder renowned for his dominant box-to-box play and key role in Manchester City's rise to Premier League prominence.
-
D.
Hamed Bakayoko
Hamed Bakayoko was an Ivorian politician who served as Prime Minister and was a key figure in Côte d'Ivoire's post-conflict political landscape.
-
E.
Solomana Kante
Solomana Kanté was a Guinean scholar and linguist best known for inventing the N’Ko script to write Manding languages and promote literacy and cultural identity in West Africa.
- 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_69ca83e467108190abcae6a33b3d4dad |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69ccaade47cc81909b5c127dc8aa1340 |
completed | April 1, 2026, 5:19 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d05c077f008190ba1bcd82b3fe9a1d |
completed | April 4, 2026, 12:32 a.m. |
| NEDg | Description generation | batch_69d05cec61908190ae783af982db4170 |
completed | April 4, 2026, 12:35 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69d05dbf1ce081908d5c8168a9315942 |
completed | April 4, 2026, 12:39 a.m. |
Created at: March 30, 2026, 7:22 p.m.