Triple
T1357188
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Songhay languages |
E29015
|
entity |
| Predicate | spokenIn |
P2266
|
FINISHED |
| Object | Timbuktu |
E144680
|
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: Timbuktu | Statement: [Songhay languages, spokenIn, Timbuktu]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Timbuktu Context triple: [Songhay languages, spokenIn, Timbuktu]
-
A.
Timbuktu
chosen
Timbuktu is an ancient city in Mali famed as a historic center of trans-Saharan trade and Islamic scholarship.
-
B.
Tanta
Tanta is a major city in northern Egypt that serves as an important commercial and transportation hub in the Nile Delta.
-
C.
Téboursouk
Téboursouk is a town in northern Tunisia known as a gateway to the nearby ancient Roman ruins of Dougga.
-
D.
Gash‑Barka
Gash‑Barka is a largely agricultural region in southwestern Eritrea known for its fertile land and role as one of the country’s main food-producing areas.
-
E.
Qunu
Qunu is a rural village in South Africa’s Eastern Cape province, best known as Nelson Mandela’s childhood home and final resting place.
- 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_69a498d77abc8190913bf57e5f51d2c4 |
completed | March 1, 2026, 7:51 p.m. |
| NER | Named-entity recognition | batch_69a4c28db5048190a279ee9882caaeaf |
completed | March 1, 2026, 10:49 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69acce6e264481909f7cb907486d3e08 |
completed | March 8, 2026, 1:18 a.m. |
Created at: March 1, 2026, 7:56 p.m.