Triple
T4820340
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tarim River |
E107694
|
entity |
| Predicate | hasCityOnBanks |
P7935
|
FINISHED |
| Object | Aksu |
E158489
|
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: Aksu | Statement: [Tarim River, hasCityOnBanks, Aksu]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Aksu Context triple: [Tarim River, hasCityOnBanks, Aksu]
-
A.
Aksu
chosen
Aksu is a city in northwestern China’s Xinjiang Uyghur Autonomous Region, known as an important oasis and agricultural center along the historic Silk Road.
-
B.
Aksu
Aksu is a modern town in Antalya Province, Turkey, located near the ancient city of Perge and known for its agricultural production and growing tourism.
-
C.
Quchan
Quchan is a historic city in northeastern Iran known for its strategic location along trade routes and its role as a regional center in the Khorasan area.
-
D.
Kyzyl-Suu
Kyzyl-Suu is a town in eastern Kyrgyzstan that serves as a local center near the southern shore of Lake Issyk-Kul.
-
E.
Hotan
Hotan is an oasis city in southwestern Xinjiang, China, historically known as a key Silk Road hub famed for its jade, silk, and carpets.
- 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_69bd43f9efa081908314cb3e94fa1695 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd6c98358081908ed43425af667a98 |
completed | March 20, 2026, 3:49 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69be4dc02118819093f4dfad16c6085f |
completed | March 21, 2026, 7:50 a.m. |
Created at: March 20, 2026, 1:24 p.m.