Triple
T13918577
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tengri |
E334683
|
entity |
| Predicate | title |
P38
|
FINISHED |
| Object | Kök Tengri |
E334683
|
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: Kök Tengri | Statement: [Tengri, title, Kök Tengri]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kök Tengri Context triple: [Tengri, title, Kök Tengri]
-
A.
Tengri
chosen
Tengri is the supreme sky god in ancient Turkic and Mongolic religions, revered as the creator and ruler of the universe.
-
B.
Chagan
Chagan is a river whose name is transliterated as "Chagan," commonly referring to waterways in parts of Central Asia and Russia.
-
C.
Toktogul
Toktogul is a town in central Kyrgyzstan known for its proximity to the Toktogul Reservoir and its role in regional hydropower and agriculture.
-
D.
Minhe Monguor
Minhe Monguor is a Mongolic language variety spoken by the Monguor (Tu) people in Minhe County, Qinghai Province, China.
-
E.
Orshuun Gol
Orshuun Gol is a river that serves as one of the main tributaries feeding Hulun Lake in northeastern Asia.
- 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_69d81c5f739081908bc05b2461f54828 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de272753e48190bc609482635280ff |
completed | April 14, 2026, 11:38 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f7ce7a1c388190a57dfdbbb732bbcb |
completed | May 3, 2026, 10:38 p.m. |
Created at: April 9, 2026, 10:16 p.m.