Triple
T17074369
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ariq Böke |
E414310
|
entity |
| Predicate | father |
P120
|
FINISHED |
| Object | Tolui |
E136173
|
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: Tolui | Statement: [Ariq Böke, father, Tolui]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tolui Context triple: [Ariq Böke, father, Tolui]
-
A.
Tolui
chosen
Tolui was a prominent Mongol general and the fourth son of Genghis Khan, known for his key role in expanding and consolidating the Mongol Empire.
-
B.
Satank
Satank was a prominent 19th-century Kiowa war leader and medicine man known for his resistance to U.S. expansion onto Native American lands.
-
C.
Khamnigan Mongol
Khamnigan Mongol is a Mongolic language spoken by the Khamnigan people in the border regions of Mongolia, Russia, and China, reflecting a blend of Mongolic and Tungusic linguistic influences.
-
D.
Subutai
Subutai was a brilliant 13th-century Mongol general and primary strategist of Genghis Khan and Ögedei Khan, renowned for his far-ranging campaigns and innovative military tactics across Asia and Europe.
-
E.
Temurin
Temurin is a high-quality, open-source Java runtime distribution provided by the Eclipse Adoptium project.
- 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_69d886cef44c8190ba56c44b4e863e64 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3dbc3b69c819093b32da3998eed46 |
completed | April 18, 2026, 7:30 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a012ede108881909ddd0455be53ffac |
completed | May 11, 2026, 1:20 a.m. |
Created at: April 10, 2026, 5:34 a.m.