Triple

T21588333
Position Surface form Disambiguated ID Type / Status
Subject Chengzong E532710 entity
Predicate alsoKnownAs P39 FINISHED
Object Temür 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: Temür | Statement: [Chengzong, alsoKnownAs, Temür]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Temür
Context triple: [Chengzong, alsoKnownAs, Temür]
  • A. Köke Temür
    Köke Temür was a prominent 14th-century Mongol general and statesman of the Yuan dynasty, known for his military campaigns and efforts to defend Mongol rule in China.
  • B. Timuri
    Timuri are a small ethnic group in Afghanistan and Iran, traditionally semi-nomadic and known for their distinct dialect and cultural practices within the broader Aimaq community.
  • C. Temür Khan chosen
    Temür Khan was a Yuan dynasty emperor and grandson of Kublai Khan who ruled China and the Mongol Empire in the late 13th and early 14th centuries.
  • D. Temurin
    Temurin is a high-quality, open-source Java runtime distribution provided by the Eclipse Adoptium project.
  • E. Toghrul Beg
    Toghrul Beg was the 11th-century Turkic leader who established Seljuk power in the Islamic world and became the first sultan of the Seljuk dynasty.
  • 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_69e0c46251648190876f0427cf2d321b completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69eeeb621ab88190a33a943424ffb306 completed April 27, 2026, 4:51 a.m.
Created at: April 16, 2026, 6:31 p.m.