Triple
T19409516
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bukhari Tajik |
E485551
|
entity |
| Predicate | hasAlternativeName |
P39
|
FINISHED |
| Object | Bukharic |
—
|
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: Bukharic | Statement: [Bukhari Tajik, hasAlternativeName, Bukharic]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bukharic Context triple: [Bukhari Tajik, hasAlternativeName, Bukharic]
-
A.
Bukharic
chosen
Bukharic is a Jewish dialect of Tajik spoken historically by the Bukharan Jewish community of Central Asia.
-
B.
Khwarezmian language
The Khwarezmian language was an extinct East Iranian language once spoken in the historical region of Khwarezm, in present-day Central Asia.
-
C.
Karakalpak language
The Karakalpak language is a Turkic language spoken primarily by the Karakalpak people in Karakalpakstan, an autonomous republic within Uzbekistan.
-
D.
Karakhani language
The Karakhani language was a historical Turkic language of the Karluk branch, associated with the Karakhanid Khanate in Central Asia.
-
E.
Bashkir language
The Bashkir language is a Turkic language spoken primarily by the Bashkir people in Russia, especially in the Republic of Bashkortostan.
- 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_69d8e8d5162481909db12435d9535c1a |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e62af3eaa081909e9537a2c57dc6c1 |
completed | April 20, 2026, 1:32 p.m. |
Created at: April 10, 2026, 1:37 p.m.