Triple
T3799578
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fezzan campaign |
E91654
|
entity |
| Predicate | location |
P40
|
FINISHED |
| Object | Fezzan |
E22133
|
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: Fezzan | Statement: [Fezzan campaign, location, Fezzan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Fezzan Context triple: [Fezzan campaign, location, Fezzan]
-
A.
Fezzan
chosen
Fezzan is a sparsely populated desert region in southwestern Libya, historically significant as a trans-Saharan trade hub and home to several ancient oasis settlements.
-
B.
Tadjourah Region
Tadjourah Region is an administrative region in western Djibouti known for its arid landscapes and for encompassing Lake Assal, one of the saltiest and lowest-lying lakes in the world.
-
C.
Toshka
Toshka is a region in southern Egypt best known for the Toshka Lakes and large-scale desert reclamation and irrigation projects near Lake Nasser.
-
D.
Gash-Barka Region
Gash-Barka Region is a largely rural administrative region in western Eritrea known for its agricultural importance and strategic location bordering Sudan and Ethiopia.
-
E.
El Azizia, Algeria
El Azizia is a small town in Algeria notable as the birthplace of prominent diplomat Lakhdar Brahimi.
- 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_69aed96354f48190a768966d6bd19b04 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aee7a43c408190a54cff649f63e69f |
completed | March 9, 2026, 3:30 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b4fb232650819089feed9d5bb8c91a |
completed | March 14, 2026, 6:07 a.m. |
Created at: March 9, 2026, 3:15 p.m.