Triple
T10486713
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Northern Niger |
E247318
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object | Bilma Erg |
E727099
|
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: Bilma Erg | Statement: [Northern Niger, contains, Bilma Erg]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bilma Erg Context triple: [Northern Niger, contains, Bilma Erg]
-
A.
Bilma
chosen
Bilma is an oasis town in northeastern Niger, historically significant as a key stop on trans-Saharan trade routes and known for its traditional salt production.
-
B.
Seyhun
Seyhun is the historical name used in Islamic and Central Asian sources for the Syr Darya River, one of the major rivers of Central Asia.
-
C.
Zübeyir
Zübeyir is a Turkish masculine given name, notably borne by the archaeologist and ethnographer Hamit Zübeyir Koşay.
-
D.
Dursunbey
Dursunbey is a town and district in western Turkey known for its forestry, timber production, and rural character within Balıkesir Province.
-
E.
Kadir
Kadir is a masculine given name of Turkish origin commonly used in Turkey and among Turkish-speaking communities.
- 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_69d381c309b88190af78aa681cf6a4c2 |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d5096a4d3481908e9c319f6cdce4f1 |
completed | April 7, 2026, 1:40 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d8dc8c73748190b97c78af6cf142d9 |
completed | April 10, 2026, 11:18 a.m. |
Created at: April 6, 2026, 12:23 p.m.