Triple

T3360849
Position Surface form Disambiguated ID Type / Status
Subject Vinod Khosla E70715 entity
Predicate spouse P13 FINISHED
Object Neeru Khosla
Neeru Khosla is an Indian-American education advocate and co-founder of the nonprofit digital learning platform CK-12 Foundation.
 E351367 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: Neeru Khosla | Statement: [Vinod Khosla, spouse, Neeru Khosla]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Neeru Khosla
Context triple: [Vinod Khosla, spouse, Neeru Khosla]
  • A. Mona Kapoor
    Mona Kapoor was an Indian television and film producer best known as the first wife of Bollywood film producer Boney Kapoor and mother of actor Arjun Kapoor.
  • B. Meena Khadikar
    Meena Khadikar is an Indian playback singer and composer, known for her work in Marathi and Hindi music and as a member of the renowned Mangeshkar musical family.
  • C. Dimple Kapadia
    Dimple Kapadia is a renowned Indian film actress known for her work in Hindi cinema since the 1970s, acclaimed for both mainstream and critically lauded roles.
  • D. Beena Pal
    Beena Pal was the wife of Indian nationalist leader and freedom fighter Bipin Chandra Pal.
  • E. Karisma Kapoor
    Karisma Kapoor is an acclaimed Indian film actress best known for her leading roles in popular Hindi movies of the 1990s and early 2000s.
  • 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: Neeru Khosla
Triple: [Vinod Khosla, spouse, Neeru Khosla]
Generated description
Neeru Khosla is an Indian-American education advocate and co-founder of the nonprofit digital learning platform CK-12 Foundation.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Neeru Khosla
Target entity description: Neeru Khosla is an Indian-American education advocate and co-founder of the nonprofit digital learning platform CK-12 Foundation.
  • A. Mona Kapoor
    Mona Kapoor was an Indian television and film producer best known as the first wife of Bollywood film producer Boney Kapoor and mother of actor Arjun Kapoor.
  • B. Meena Khadikar
    Meena Khadikar is an Indian playback singer and composer, known for her work in Marathi and Hindi music and as a member of the renowned Mangeshkar musical family.
  • C. Dimple Kapadia
    Dimple Kapadia is a renowned Indian film actress known for her work in Hindi cinema since the 1970s, acclaimed for both mainstream and critically lauded roles.
  • D. Beena Pal
    Beena Pal was the wife of Indian nationalist leader and freedom fighter Bipin Chandra Pal.
  • E. Karisma Kapoor
    Karisma Kapoor is an acclaimed Indian film actress best known for her leading roles in popular Hindi movies of the 1990s and early 2000s.
  • 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_69ad85a660c48190998489309a3b4869 completed March 8, 2026, 2:20 p.m.
NER Named-entity recognition batch_69adb267ec1081909a4e3e227d5bad01 completed March 8, 2026, 5:31 p.m.
NED1 Entity disambiguation (via context triple) batch_69b32546651481908dc6ab15b3344788 completed March 12, 2026, 8:42 p.m.
NEDg Description generation batch_69b3280b712c8190875d5d35a1795bcd completed March 12, 2026, 8:54 p.m.
NED2 Entity disambiguation (via description) batch_69b328ad98cc819092f5b92eb4abd1b7 completed March 12, 2026, 8:57 p.m.
Created at: March 8, 2026, 3:13 p.m.