Triple

T23349744
Position Surface form Disambiguated ID Type / Status
Subject Initialized Capital E591971 entity
Predicate coFoundedBy P3263 FINISHED
Object Harjeet Taggar
Harjeet Taggar is a technology investor and entrepreneur best known as a co-founder of Initialized Capital and former partner at Y Combinator.
E1582090 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: Harjeet Taggar | Statement: [Initialized Capital, coFoundedBy, Harjeet Taggar]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Harjeet Taggar
Context triple: [Initialized Capital, coFoundedBy, Harjeet Taggar]
  • A. Amarjeet Sohi
    Amarjeet Sohi is a Canadian politician who serves as the mayor of Edmonton and is a former federal cabinet minister.
  • B. Shaan Singh
    Shaan Singh is a musician best known as a member of the band The Hooligans.
  • C. Daljit Nagra
    Daljit Nagra is a British poet known for his innovative use of Punjabi-inflected English and acclaimed collections exploring British-Asian identity.
  • D. Charanjit Jutla
    Charanjit Jutla is a cryptographer known for his research contributions in theoretical computer science and cryptographic protocols.
  • E. Baljeet Tjinder
    Baljeet Tjinder is a studious, academically driven boy in the animated series "Phineas and Ferb," known for his intelligence, anxiety about grades, and frequent involvement in the protagonists’ inventions and adventures.
  • 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: Harjeet Taggar
Triple: [Initialized Capital, coFoundedBy, Harjeet Taggar]
Generated description
Harjeet Taggar is a technology investor and entrepreneur best known as a co-founder of Initialized Capital and former partner at Y Combinator.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Harjeet Taggar
Target entity description: Harjeet Taggar is a technology investor and entrepreneur best known as a co-founder of Initialized Capital and former partner at Y Combinator.
  • A. Amarjeet Sohi
    Amarjeet Sohi is a Canadian politician who serves as the mayor of Edmonton and is a former federal cabinet minister.
  • B. Shaan Singh
    Shaan Singh is a musician best known as a member of the band The Hooligans.
  • C. Daljit Nagra
    Daljit Nagra is a British poet known for his innovative use of Punjabi-inflected English and acclaimed collections exploring British-Asian identity.
  • D. Charanjit Jutla
    Charanjit Jutla is a cryptographer known for his research contributions in theoretical computer science and cryptographic protocols.
  • E. Baljeet Tjinder
    Baljeet Tjinder is a studious, academically driven boy in the animated series "Phineas and Ferb," known for his intelligence, anxiety about grades, and frequent involvement in the protagonists’ inventions and adventures.
  • 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_69e25d20e3d08190bcede87673cafb25 completed April 17, 2026, 4:17 p.m.
NER Named-entity recognition batch_69f19a132da08190b30de610d34c96cc completed April 29, 2026, 5:41 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0c4cbbbf388190a2ec51bb06690168 completed May 19, 2026, 11:42 a.m.
NEDg Description generation batch_6a0c59a18c5481909662cd338b797340 completed May 19, 2026, 12:37 p.m.
NED2 Entity disambiguation (via description) batch_6a0c5a57cfb88190bb4e7f65807639b6 completed May 19, 2026, 12:40 p.m.
Created at: April 17, 2026, 5:19 p.m.