Triple
T21258704
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gaochang Ruins |
E523938
|
entity |
| Predicate | historicalName |
P65
|
FINISHED |
| Object | Karakhoja |
—
|
NE NERFINISHED |
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: Karakhoja | Statement: [Gaochang Ruins, historicalName, Karakhoja]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Karakhoja Context triple: [Gaochang Ruins, historicalName, Karakhoja]
-
A.
Karakhoja
chosen
Karakhoja is the historical name for Gaochang, an ancient Silk Road oasis city and Buddhist cultural center near modern Turpan in Xinjiang, China.
-
B.
Chaghasarai
Chaghasarai is the former name of Asadabad, a city in western Iran that serves as the capital of Hamadan Province’s Asadabad County.
-
C.
Khiva
Khiva is an ancient oasis city in western Uzbekistan renowned for its well-preserved walled old town, Itchan Kala, a UNESCO World Heritage Site.
-
D.
Karshi oasis
Karshi oasis is a fertile agricultural region in southern Uzbekistan, sustained by irrigation and known historically as a key settlement area along Central Asian trade routes.
-
E.
Shemakhan
Shemakhan is a fictional realm best known as the exotic homeland of the seductive Queen of Shemakha in Russian literature and opera.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0b5156d7881909bd4f83676590715 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e735e477d08190be17ad5384d69a80 |
completed | April 21, 2026, 8:31 a.m. |
Created at: April 16, 2026, 3:59 p.m.