Triple
T3296066
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Golden Horde |
E69217
|
entity |
| Predicate | ruler |
P403
|
FINISHED |
| Object | Tokhtamysh |
E336889
|
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: Tokhtamysh | Statement: [Golden Horde, ruler, Tokhtamysh]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tokhtamysh Context triple: [Golden Horde, ruler, Tokhtamysh]
-
A.
Tokhtamysh
chosen
Tokhtamysh was a late 14th-century khan of the Golden Horde who briefly reunited its territories and clashed with the Central Asian conqueror Timur.
-
B.
Qazan Khan
Qazan Khan was a 14th-century ruler of the Chagatai Khanate, a Mongol successor state in Central Asia descended from Genghis Khan’s empire.
-
C.
Uzbek Khan
Uzbek Khan was a powerful 14th-century khan of the Golden Horde known for making Islam the state religion and overseeing a period of political stability and economic prosperity.
-
D.
Nogai Khan
Nogai Khan was a powerful Mongol general and de facto ruler in the western part of the Golden Horde during the late 13th century.
-
E.
Nogai
Nogai is a Turkic language spoken primarily by the Nogai people of the North Caucasus region in Russia.
- 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_69ad859e529c8190a404273f53cb487d |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adb077c60c81909782be5202ce5a43 |
completed | March 8, 2026, 5:23 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b402c197c88190b0ca5a7f47141511 |
completed | March 13, 2026, 12:27 p.m. |
Created at: March 8, 2026, 3:10 p.m.