Triple

T15989335
Position Surface form Disambiguated ID Type / Status
Subject Roelof Botha E387781 entity
Predicate boardMemberOf P10 FINISHED
Object Natera
Natera is a biotechnology company specializing in genetic testing and diagnostics, particularly in reproductive health, oncology, and organ health.
E1187497 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: Natera | Statement: [Roelof Botha, boardMemberOf, Natera]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Natera
Context triple: [Roelof Botha, boardMemberOf, Natera]
  • A. Veritas Genetics
    Veritas Genetics is a biotechnology company that offers whole-genome sequencing and interpretation services for consumers and clinicians.
  • B. Innogen
    Innogen is the original name of Imogen, the virtuous and wronged heroine of William Shakespeare’s play "Cymbeline."
  • C. Genex
    Genex is an airline that uses Minsk National Airport as a primary base of operations for its flight network.
  • D. Ventris
    Ventris is the surname of Michael Ventris, the British architect and linguist renowned for deciphering the ancient script Linear B.
  • E. Nebula Genomics
    Nebula Genomics is a personal genomics company that offers whole-genome sequencing and analysis with a focus on privacy-preserving, blockchain-based data sharing.
  • 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: Natera
Triple: [Roelof Botha, boardMemberOf, Natera]
Generated description
Natera is a biotechnology company specializing in genetic testing and diagnostics, particularly in reproductive health, oncology, and organ health.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Natera
Target entity description: Natera is a biotechnology company specializing in genetic testing and diagnostics, particularly in reproductive health, oncology, and organ health.
  • A. Veritas Genetics
    Veritas Genetics is a biotechnology company that offers whole-genome sequencing and interpretation services for consumers and clinicians.
  • B. Innogen
    Innogen is the original name of Imogen, the virtuous and wronged heroine of William Shakespeare’s play "Cymbeline."
  • C. Genex
    Genex is an airline that uses Minsk National Airport as a primary base of operations for its flight network.
  • D. Ventris
    Ventris is the surname of Michael Ventris, the British architect and linguist renowned for deciphering the ancient script Linear B.
  • E. Nebula Genomics
    Nebula Genomics is a personal genomics company that offers whole-genome sequencing and analysis with a focus on privacy-preserving, blockchain-based data sharing.
  • 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_69d86daa562c81908aacc179c0fe8fb5 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e157829ec08190aa4a683e29a0148a completed April 16, 2026, 9:41 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffc3d2369081909efa2d4addf0cf2d completed May 9, 2026, 11:31 p.m.
NEDg Description generation batch_69ffc45e6ff48190bb7b82adb4161ad0 completed May 9, 2026, 11:33 p.m.
NED2 Entity disambiguation (via description) batch_69ffc4cea4108190927b107fc24df597 completed May 9, 2026, 11:35 p.m.
Created at: April 10, 2026, 4:54 a.m.