Triple
T8384140
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ghadamès Berber language |
E197770
|
entity |
| Predicate | spokenIn |
P2266
|
FINISHED |
| Object | Ghadamès |
E39478
|
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: Ghadamès | Statement: [Ghadamès Berber language, spokenIn, Ghadamès]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ghadamès Context triple: [Ghadamès Berber language, spokenIn, Ghadamès]
-
A.
Ghadamès
chosen
Ghadamès is an ancient oasis town in western Libya, renowned for its well-preserved Saharan architecture and UNESCO-listed historic old quarter.
-
B.
Kassala
Kassala is a city in eastern Sudan near the Eritrean border, known as a regional trade center and for its striking granite hills and cultural diversity.
-
C.
Galkayo
Galkayo is a major city in central Somalia that serves as an important commercial and administrative hub for the surrounding region.
-
D.
Zintan
Zintan is a town in western Libya known for its role in the Libyan Civil War and for being controlled by powerful local militias.
-
E.
Habash
Habash is an Arabic surname most notably associated with George Habash, the Palestinian Christian physician and founder of the Popular Front for the Liberation of Palestine.
- 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_69ca82f64c188190af4e1608036b865d |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cb80ded0ec81909771482e1a015a67 |
completed | March 31, 2026, 8:07 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ce1d14baf88190bc260efda7d0fc0d |
completed | April 2, 2026, 7:39 a.m. |
Created at: March 30, 2026, 6:02 p.m.