Triple
T5459711
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shanshan |
E122566
|
entity |
| Predicate | capital |
P234
|
FINISHED |
| Object | Loulan |
E125348
|
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: Loulan | Statement: [Shanshan, capital, Loulan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Loulan Context triple: [Shanshan, capital, Loulan]
-
A.
Loulan
chosen
Loulan was an ancient Silk Road kingdom and oasis city in the eastern Tarim Basin, known for its strategic location and well-preserved archaeological remains.
-
B.
Daiyuan
Daiyuan is a given name most notably associated with Teng Daiyuan, a prominent Chinese Communist revolutionary and political leader.
-
C.
Chardzhou
Chardzhou is the former name of Turkmenabat, a major city in eastern Turkmenistan located on the Amu Darya River.
-
D.
Kharan District
Kharan District is an administrative district in the Balochistan province of Pakistan, known for its arid desert landscape and sparse population.
-
E.
Dunhuang
Dunhuang is an ancient oasis city in northwestern China renowned for its strategic position as a gateway between China and Central Asia and for the nearby Mogao Caves filled with Buddhist art.
- 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_69bd46424248819085282ddf50a565f3 |
completed | March 20, 2026, 1:06 p.m. |
| NER | Named-entity recognition | batch_69bd91f353c481909ae1a73ae419fb9a |
completed | March 20, 2026, 6:29 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bf488866088190b213bd641f8b247c |
completed | March 22, 2026, 1:40 a.m. |
Created at: March 20, 2026, 2:08 p.m.