Triple
T6771784
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Direction Nationale des Langues Nationales du Mali |
E155060
|
entity |
| Predicate | worksOnLanguage |
P18404
|
FINISHED |
| Object |
Bozo
Bozo is a Mande language spoken primarily by the Bozo people of Mali, especially along the Niger River.
|
E618747
|
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: Bozo | Statement: [Direction Nationale des Langues Nationales du Mali, worksOnLanguage, Bozo]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bozo Context triple: [Direction Nationale des Langues Nationales du Mali, worksOnLanguage, Bozo]
-
A.
Bobo
Bobo is a major Mande language spoken primarily in parts of West Africa, notably in Burkina Faso and Mali.
-
B.
Bo
Bo was an extinct indigenous language of the Great Andamanese people, once spoken in the Andaman Islands of India.
-
C.
Bo
Bo was the Portuguese Water Dog who served as one of the Obama family's beloved First Pets during Barack Obama's presidency.
-
D.
Bo
Bo is the widely known nickname of legendary American college football coach Bo Schembechler, famed for his long tenure at the University of Michigan.
-
E.
Bo
Bo is the widely used nickname of Bo Jackson, the legendary American multi-sport athlete who excelled in both professional baseball and football.
- 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: Bozo Triple: [Direction Nationale des Langues Nationales du Mali, worksOnLanguage, Bozo]
Generated description
Bozo is a Mande language spoken primarily by the Bozo people of Mali, especially along the Niger River.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Bozo Target entity description: Bozo is a Mande language spoken primarily by the Bozo people of Mali, especially along the Niger River.
-
A.
Bobo
Bobo is a major Mande language spoken primarily in parts of West Africa, notably in Burkina Faso and Mali.
-
B.
Bo
Bo was an extinct indigenous language of the Great Andamanese people, once spoken in the Andaman Islands of India.
-
C.
Bo
Bo was the Portuguese Water Dog who served as one of the Obama family's beloved First Pets during Barack Obama's presidency.
-
D.
Bo
Bo is the widely used nickname of Bo Jackson, the legendary American multi-sport athlete who excelled in both professional baseball and football.
-
E.
Bo
Bo is the widely known nickname of legendary American college football coach Bo Schembechler, famed for his long tenure at the University of Michigan.
- 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_69c68812ef7c819099369f51febb725c |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6d7c94bac8190ae4b236d1b04bec9 |
completed | March 27, 2026, 7:17 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c712c75b9c819099b0be616925a0b9 |
completed | March 27, 2026, 11:29 p.m. |
| NEDg | Description generation | batch_69c7135106288190b5b20523c3efa229 |
completed | March 27, 2026, 11:31 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69c7141cd52c8190a783590ad1067840 |
completed | March 27, 2026, 11:34 p.m. |
Created at: March 27, 2026, 2:13 p.m.