Triple
T2380305
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of Talas |
E46295
|
entity |
| Predicate | relatedTo |
P37
|
FINISHED |
| Object | Fergana Valley |
E82439
|
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 Valley | Statement: [Battle of Talas, relatedTo, Fergana Valley]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Fergana Valley Context triple: [Battle of Talas, relatedTo, Fergana Valley]
-
A.
Ferghana Valley
chosen
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.
-
B.
Fergana
Fergana is a major city in eastern Uzbekistan, known as an administrative, cultural, and industrial center of the fertile Fergana Valley.
-
C.
Issyk-Kul Region
Issyk-Kul Region is an eastern province of Kyrgyzstan famed for its high-altitude Issyk-Kul Lake and its location amid the Tien Shan mountain range.
-
D.
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.
-
E.
Yaghnobi
Yaghnobi is an Eastern Iranian language spoken by the Yaghnobi people of Tajikistan, considered a direct descendant of ancient Sogdian.
- 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_69a88a1554a48190a0180682bcf099be |
completed | March 4, 2026, 7:37 p.m. |
| NER | Named-entity recognition | batch_69abc7b60c8c819080e4f682e4362a93 |
completed | March 7, 2026, 6:37 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69aebf36dcac8190a17d9af8cd1660c4 |
completed | March 9, 2026, 12:38 p.m. |
Created at: March 4, 2026, 7:57 p.m.