Triple

T21713901
Position Surface form Disambiguated ID Type / Status
Subject Temür Khan E535972 entity
Predicate mother P120 FINISHED
Object Kökejin NE NERFINISHED

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: Kökejin | Statement: [Temür Khan, mother, Kökejin]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kökejin
Context triple: [Temür Khan, mother, Kökejin]
  • A. Kökejin chosen
    Kökejin was a Mongol noblewoman of the Yuan dynasty best known as the mother of Emperor Temür Khan.
  • B. Kökeqota
    Kökeqota is a historic city in what is now Hohhot, Inner Mongolia, that served as the principal political and administrative center of the Northern Yuan dynasty after the fall of the Yuan in China.
  • C. Kasagi
    Kasagi is a small town in Kyoto Prefecture, Japan, known for its scenic river landscapes and historic temples.
  • D. Kokonor
    Kokonor is the Mongolian name for Qinghai Lake, a large saline lake on the northeastern Tibetan Plateau in China.
  • E. Uzkoye
    Uzkoye is a historic estate and former village in the south of Moscow, Russia, known for its noble residences and integration into the modern city.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e0c46c6dd88190a595375fa6ebd701 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69efb5369be88190bafc10863d4d1bd7 completed April 27, 2026, 7:12 p.m.
Created at: April 16, 2026, 6:47 p.m.