Triple

T6207991
Position Surface form Disambiguated ID Type / Status
Subject Kayqubad I E138794 entity
Predicate usedTitle P3254 FINISHED
Object Alaeddin
Alaeddin (often rendered Alā al-Dīn) was an honorific title meaning "nobility of the faith," historically borne by various Muslim rulers and notable figures, including the Seljuk sultan Kayqubad I.
 E473974 NE FINISHED

How this triple was built (4 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: Alaeddin | Statement: [Kayqubad I, usedTitle, Alaeddin]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Alaeddin
Context triple: [Kayqubad I, usedTitle, Alaeddin]
  • A. Alaeddin
    Alaeddin was an early Ottoman statesman and son of Osman I, often regarded as the first Ottoman grand vizier.
  • B. Gawhar Shad
    Gawhar Shad was a powerful and influential Timurid queen and patron of art and architecture in 15th-century Persia and Central Asia.
  • C. Malek
    Malek is a given name and surname of Arabic origin commonly used across the Middle East and other Muslim-majority regions.
  • D. Eskandar
    Eskandar is a Persian and Arabic form of the name Alexander, commonly used in historical and literary contexts to refer to Alexander the Great.
  • E. Jaffar
    Jaffar is the sinister vizier and main antagonist portrayed by Conrad Veidt in the 1940 fantasy film "The Thief of Bagdad."
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Alaeddin
Triple: [Kayqubad I, usedTitle, Alaeddin]
Generated description
Alaeddin (often rendered Alā al-Dīn) was an honorific title meaning "nobility of the faith," historically borne by various Muslim rulers and notable figures, including the Seljuk sultan Kayqubad I.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Alaeddin
Target entity description: Alaeddin (often rendered Alā al-Dīn) was an honorific title meaning "nobility of the faith," historically borne by various Muslim rulers and notable figures, including the Seljuk sultan Kayqubad I.
  • A. Alaeddin chosen
    Alaeddin was an early Ottoman statesman and son of Osman I, often regarded as the first Ottoman grand vizier.
  • B. Gawhar Shad
    Gawhar Shad was a powerful and influential Timurid queen and patron of art and architecture in 15th-century Persia and Central Asia.
  • C. Malek
    Malek is a given name and surname of Arabic origin commonly used across the Middle East and other Muslim-majority regions.
  • D. Eskandar
    Eskandar is a Persian and Arabic form of the name Alexander, commonly used in historical and literary contexts to refer to Alexander the Great.
  • E. Jaffar
    Jaffar is the sinister vizier and main antagonist portrayed by Conrad Veidt in the 1940 fantasy film "The Thief of Bagdad."
  • F. None of above.

Provenance (5 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_69c008ada364819096c9e92c74d639b5 completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c062870d5881909b8d4e33ff31a907 completed March 22, 2026, 9:43 p.m.
NED1 Entity disambiguation (via context triple) batch_69c16f4ce8888190b5cc4f1b091e88f3 completed March 23, 2026, 4:50 p.m.
NEDg Description generation batch_69c1e69150ac81909f7247ba3dd1e373 completed March 24, 2026, 1:19 a.m.
NED2 Entity disambiguation (via description) batch_69c1e71bd420819082d802f810baa61e completed March 24, 2026, 1:21 a.m.
Created at: March 22, 2026, 4:20 p.m.