Triple
T9014926
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Susu |
E215569
|
entity |
| Predicate | neighboringPeoples |
P11274
|
FINISHED |
| Object | Mandinka |
E28118
|
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: Mandinka | Statement: [Susu, neighboringPeoples, Mandinka]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mandinka Context triple: [Susu, neighboringPeoples, Mandinka]
-
A.
Mandinka
chosen
Mandinka is a major Mande language spoken primarily in The Gambia, Senegal, Guinea-Bissau, and neighboring West African countries by the Mandinka people.
-
B.
Mandeali
Mandeali is an Indo-Aryan language spoken primarily in the Mandi district of Himachal Pradesh in northern India.
-
C.
Mundemba
Mundemba is a town in southwestern Cameroon known as a gateway to the biodiverse Korup National Park.
-
D.
Zande
Zande is a Central African language spoken primarily by the Azande people across parts of South Sudan, the Central African Republic, and the Democratic Republic of the Congo.
-
E.
Jolu
Jolu is a character in Cory Doctorow's novel "Little Brother," known as one of Marcus Yallow's close friends and fellow teenage hackers resisting government surveillance.
- 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_69ca83a2bf088190986ee7a8eb90407d |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc69fae0b88190a0aa989bc37ab2c7 |
completed | April 1, 2026, 12:42 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cfeb7117c48190a9dca7bbdabe9e3d |
completed | April 3, 2026, 4:31 p.m. |
Created at: March 30, 2026, 7:06 p.m.