Triple

T4850488
Position Surface form Disambiguated ID Type / Status
Subject Heptares Therapeutics E108401 entity
Predicate foundedBy P104 FINISHED
Object David Marshall
David Marshall is a biotechnology entrepreneur best known as a founder of the drug discovery company Heptares Therapeutics.
 E474946 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: David Marshall | Statement: [Heptares Therapeutics, foundedBy, David Marshall]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: David Marshall
Context triple: [Heptares Therapeutics, foundedBy, David Marshall]
  • A. David Marshall
    David Marshall was a prominent Singaporean politician and lawyer who became the country’s first Chief Minister and a leading advocate for self-governance.
  • B. Gabriel Almond
    Gabriel Almond was an influential American political scientist known for his work on comparative politics and political culture.
  • C. Paul Givan
    Paul Givan is a Democratic Unionist Party politician who served as First Minister of Northern Ireland.
  • D. John Lyons
    John Lyons is a film producer best known for his work on major Hollywood comedies, including the Austin Powers series.
  • E. Edward Hume
    Edward Hume was an American television writer and producer best known for creating and writing several popular crime and drama series in the 1970s and 1980s.
  • 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: David Marshall
Triple: [Heptares Therapeutics, foundedBy, David Marshall]
Generated description
David Marshall is a biotechnology entrepreneur best known as a founder of the drug discovery company Heptares Therapeutics.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: David Marshall
Target entity description: David Marshall is a biotechnology entrepreneur best known as a founder of the drug discovery company Heptares Therapeutics.
  • A. David Marshall
    David Marshall was a prominent Singaporean politician and lawyer who became the country’s first Chief Minister and a leading advocate for self-governance.
  • B. Gabriel Almond
    Gabriel Almond was an influential American political scientist known for his work on comparative politics and political culture.
  • C. Paul Givan
    Paul Givan is a Democratic Unionist Party politician who served as First Minister of Northern Ireland.
  • D. John Lyons
    John Lyons is a film producer best known for his work on major Hollywood comedies, including the Austin Powers series.
  • E. Edward Hume
    Edward Hume was an American television writer and producer best known for creating and writing several popular crime and drama series in the 1970s and 1980s.
  • 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_69bd440a89548190a5f14ba6da6b97dc completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd6d1e5cf08190bd6b6a524748f170 completed March 20, 2026, 3:51 p.m.
NED1 Entity disambiguation (via context triple) batch_69be5cdefda8819095fbc04446bf32f5 completed March 21, 2026, 8:54 a.m.
NEDg Description generation batch_69be5dadcec88190bf9a272c4a9aef9a completed March 21, 2026, 8:58 a.m.
NED2 Entity disambiguation (via description) batch_69be6159ff7c8190baa116240f76dea5 completed March 21, 2026, 9:14 a.m.
Created at: March 20, 2026, 1:25 p.m.