Triple
T5488314
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Saka |
E123639
|
entity |
| Predicate | hasDialect |
P4251
|
FINISHED |
| Object | Tumshuqese |
E228143
|
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: Tumshuqese | Statement: [Saka, hasDialect, Tumshuqese]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tumshuqese Context triple: [Saka, hasDialect, Tumshuqese]
-
A.
Tumshuqese
chosen
Tumshuqese is an extinct Eastern Iranian language once spoken in the region of Tumshuq in what is now Xinjiang, China.
-
B.
Tumshuq
Tumshuq is an ancient city in the Tarim Basin region of Xinjiang, China, historically associated with the Saka (Scythian) peoples and their Eastern Iranian languages.
-
C.
Humash
Humash is the Hebrew term for the Five Books of Moses, the foundational text of the Jewish Torah.
-
D.
Ishawiyen
Ishawiyen is the endonym used by the Chaoui people, an Amazigh (Berber) ethnic group indigenous to the Aurès region of northeastern Algeria.
-
E.
Ashuri
Ashuri was an ancient region or group under the rule of Ish-bosheth, a short-lived king of Israel mentioned in the Hebrew Bible.
- 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_69bd464a2d908190869324ce176779c8 |
completed | March 20, 2026, 1:06 p.m. |
| NER | Named-entity recognition | batch_69bd9264d014819097c83bb5c2bb8c39 |
completed | March 20, 2026, 6:31 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bf70dcb0c881909d9aaf0050a5c27b |
completed | March 22, 2026, 4:32 a.m. |
Created at: March 20, 2026, 2:10 p.m.