Triple
T9461327
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Khujand |
E228149
|
entity |
| Predicate | regionCode |
P208
|
FINISHED |
| Object | Sughd |
E800913
|
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: Sughd | Statement: [Khujand, regionCode, Sughd]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sughd Context triple: [Khujand, regionCode, Sughd]
-
A.
Sughd Region
chosen
Sughd Region is a northern administrative region of Tajikistan known for its mountainous terrain, historical Silk Road cities, and diverse linguistic communities.
-
B.
Karakalpak
Karakalpak is a Turkic language spoken primarily by the Karakalpak people in northwestern Uzbekistan and surrounding regions.
-
C.
Turkestan
Turkestan is a historical region in Central Asia traditionally inhabited by various Turkic peoples and spanning parts of modern-day China, Kazakhstan, Kyrgyzstan, Uzbekistan, Turkmenistan, and neighboring areas.
-
D.
Takestan
Takestan is a city in northwestern Iran known as an important agricultural and viticultural center within Qazvin Province.
-
E.
Uzbekistan
Uzbekistan is a landlocked Central Asian country known for its Silk Road heritage, including historic cities like Samarkand and Bukhara, and for being a major producer of cotton and natural gas.
- 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_69ca843b123881909b0e60028475d12d |
completed | March 30, 2026, 2:10 p.m. |
| NER | Named-entity recognition | batch_69cd7fcc8b1881908aa6ee13ab195330 |
completed | April 1, 2026, 8:27 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d16122898c8190947a821f69f957cc |
completed | April 4, 2026, 7:06 p.m. |
Created at: March 30, 2026, 7:52 p.m.