Triple
T14061880
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jochi |
E338365
|
entity |
| Predicate | child |
P120
|
FINISHED |
| Object | Shiban |
E347579
|
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: Shiban | Statement: [Jochi, child, Shiban]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Shiban Context triple: [Jochi, child, Shiban]
-
A.
Shiban
chosen
Shiban was a Mongol prince of the Golden Horde, a son of Jochi and grandson of Genghis Khan who founded the Shibanid line.
-
B.
Shinshiro
Shinshiro is a city in eastern Aichi Prefecture, Japan, known for its mountainous scenery, historic battle sites, and traditional rural landscapes.
-
C.
Seishirō
Seishirō is a Japanese given name commonly used for male individuals.
-
D.
Jeriba Shigan
Jeriba Shigan is a Drac alien pilot who becomes an unlikely ally and close companion to a human soldier in the science fiction story "Enemy Mine."
-
E.
Shige
Shige is a given name, notably used by the Chinese mathematician Peng Shige, recognized for his contributions to probability theory and stochastic analysis.
- 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_69d81c67ba6c819091935650dfb3b895 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de568876308190840361dcaf10bd45 |
completed | April 14, 2026, 3 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fcd09db51c8190ab275e68b1aec120 |
completed | May 7, 2026, 5:49 p.m. |
Created at: April 9, 2026, 10:21 p.m.