Triple
T3020392
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ferghana Valley |
E82439
|
entity |
| Predicate | majorCity |
P316
|
FINISHED |
| Object | Fergana |
E113681
|
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: Fergana | Statement: [Ferghana Valley, majorCity, Fergana]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Fergana Context triple: [Ferghana Valley, majorCity, Fergana]
-
A.
Fergana
chosen
Fergana is a major city in eastern Uzbekistan, known as an administrative, cultural, and industrial center of the fertile Fergana Valley.
-
B.
Ferghana Valley
The Ferghana Valley is a fertile and densely populated intermountain basin in Central Asia, shared mainly by Uzbekistan, Kyrgyzstan, and Tajikistan, and known as a historic crossroads of trade and culture.
-
C.
Sirdaryo
Sirdaryo is the Uzbek name for the Syr Darya, a major river in Central Asia that flows through countries such as Uzbekistan, Tajikistan, and Kazakhstan.
-
D.
Yaghnobi
Yaghnobi is an Eastern Iranian language spoken by the Yaghnobi people of Tajikistan, considered a direct descendant of ancient Sogdian.
-
E.
Karakalpak
Karakalpak is a Turkic language spoken primarily by the Karakalpak people in northwestern Uzbekistan and surrounding regions.
- 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_69ad8b1fb34081908c1b873e2b7273e1 |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69ad9a940c048190bc46e2c8001db8c0 |
completed | March 8, 2026, 3:49 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b20342ccf88190880b21f72948a4d3 |
completed | March 12, 2026, 12:05 a.m. |
Created at: March 8, 2026, 3 p.m.