Triple
T13762167
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kara Darya |
E330638
|
entity |
| Predicate | flowsNear |
P350
|
FINISHED |
| Object | Andijan |
E68252
|
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: Andijan | Statement: [Kara Darya, flowsNear, Andijan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Andijan Context triple: [Kara Darya, flowsNear, Andijan]
-
A.
Andijan
chosen
Andijan is a historic city in eastern Uzbekistan, known as a major cultural and economic center of the Fergana Valley and as the birthplace of the Mughal emperor Babur.
-
B.
Kokand
Kokand is a historic city in the Fergana Valley of present-day Uzbekistan that served as a major political, cultural, and trading center in Central Asia.
-
C.
Tashkurgan
Tashkurgan is a remote town in China’s Xinjiang region, inhabited mainly by Tajik people and known as a key stop on the Karakoram Highway near the Pakistan border.
-
D.
Qarshi
Qarshi is a historic city in southern Uzbekistan known as a regional economic and cultural center.
-
E.
Qamishli
Qamishli is a predominantly Kurdish city in northeastern Syria that serves as a key cultural and political hub for Kurmanji-speaking Kurds.
- 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_69d81c573f288190aa2403d484fa3d49 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de02250f4881908d5193b3d5d25844 |
completed | April 14, 2026, 9 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f7ce64676c8190921796666ecd3dba |
completed | May 3, 2026, 10:38 p.m. |
Created at: April 9, 2026, 10:10 p.m.