Triple

T9240015
Position Surface form Disambiguated ID Type / Status
Subject Safi I E222033 entity
Predicate mother P120 FINISHED
Object Dilaram Khanum
Dilaram Khanum was a Safavid royal consort and the mother of Shah Safi I of Persia in the 17th century.
E787038 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: Dilaram Khanum | Statement: [Safi I, mother, Dilaram Khanum]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dilaram Khanum
Context triple: [Safi I, mother, Dilaram Khanum]
  • A. Tajlu Khanum
    Tajlu Khanum was a prominent Safavid royal consort and queen mother, best known as the influential mother of Shah Tahmasp I of Iran.
  • B. Shah Khanum
    Shah Khanum was the grandmother of Siraj ud-Daulah, the last independent Nawab of Bengal in the mid-18th century.
  • C. Qutlugh Nigar Khanum
    Qutlugh Nigar Khanum was a Timurid princess and consort who became historically notable as the mother of Babur, the founder of the Mughal Empire.
  • D. Kandahari Begum
    Kandahari Begum was a Mughal princess and the first wife of Emperor Shah Jahan, known for her Timurid lineage and political significance in the Mughal court.
  • E. Saray Mulk Khanum
    Saray Mulk Khanum was a prominent 14th-century Central Asian noblewoman and chief consort of the conqueror Timur, noted for her political influence and patronage of architecture in the Timurid court.
  • 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: Dilaram Khanum
Triple: [Safi I, mother, Dilaram Khanum]
Generated description
Dilaram Khanum was a Safavid royal consort and the mother of Shah Safi I of Persia in the 17th century.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Dilaram Khanum
Target entity description: Dilaram Khanum was a Safavid royal consort and the mother of Shah Safi I of Persia in the 17th century.
  • A. Tajlu Khanum
    Tajlu Khanum was a prominent Safavid royal consort and queen mother, best known as the influential mother of Shah Tahmasp I of Iran.
  • B. Shah Khanum
    Shah Khanum was the grandmother of Siraj ud-Daulah, the last independent Nawab of Bengal in the mid-18th century.
  • C. Qutlugh Nigar Khanum
    Qutlugh Nigar Khanum was a Timurid princess and consort who became historically notable as the mother of Babur, the founder of the Mughal Empire.
  • D. Kandahari Begum
    Kandahari Begum was a Mughal princess and the first wife of Emperor Shah Jahan, known for her Timurid lineage and political significance in the Mughal court.
  • E. Saray Mulk Khanum
    Saray Mulk Khanum was a prominent 14th-century Central Asian noblewoman and chief consort of the conqueror Timur, noted for her political influence and patronage of architecture in the Timurid court.
  • F. None of above. chosen

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_69ca83ee26cc81909ac624e190597d6d completed March 30, 2026, 2:08 p.m.
NER Named-entity recognition batch_69ccf0a3888c8190b72d8d0b850bdfbc completed April 1, 2026, 10:17 a.m.
NED1 Entity disambiguation (via context triple) batch_69d077db03048190b9c1f0812da21733 completed April 4, 2026, 2:30 a.m.
NEDg Description generation batch_69d07dc19c2881909f095db0659f54db completed April 4, 2026, 2:56 a.m.
NED2 Entity disambiguation (via description) batch_69d07e0ff9188190ba4b9c4ad17d37f5 completed April 4, 2026, 2:57 a.m.
Created at: March 30, 2026, 7:30 p.m.