Triple
T8600668
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tamahaq |
E203665
|
entity |
| Predicate | region |
P40
|
FINISHED |
| Object | Sahara Desert |
E10378
|
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: Sahara Desert | Statement: [Tamahaq, region, Sahara Desert]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sahara Desert Context triple: [Tamahaq, region, Sahara Desert]
-
A.
Sahara Desert
chosen
The Sahara Desert is the world’s largest hot desert, spanning much of North Africa with vast sand seas, rocky plateaus, and extreme arid conditions.
-
B.
Sahara
Sahara is an OpenStack data processing service that provisions and manages Hadoop and other big data clusters on cloud infrastructure.
-
C.
Sahara
"Sahara" is a 2005 action-adventure film based on Clive Cussler's novel, following treasure hunters on a perilous quest in the African desert.
-
D.
Arabian Desert
The Arabian Desert is a vast arid region spanning much of the Arabian Peninsula, known for its extreme climate, expansive sand dunes, and significant oil-rich subsoil.
-
E.
Libyan Desert
The Libyan Desert is a harsh, arid expanse in the eastern Sahara, spanning parts of Libya and neighboring countries and characterized by vast sand seas, rocky plateaus, and extreme climatic conditions.
- 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_69ca832b56948190ba751cec255308f1 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cc46d8ff408190acc7cd8dc99b2689 |
completed | March 31, 2026, 10:12 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cea868de6881908e87270a1fea0e4b |
completed | April 2, 2026, 5:33 p.m. |
Created at: March 30, 2026, 6:24 p.m.