Triple

T623287
Position Surface form Disambiguated ID Type / Status
Subject Darwin manuscripts E14558 entity
Predicate hasDigitalRepresentation P8017 FINISHED
Object Darwin Manuscripts Project at the American Museum of Natural History
The Darwin Manuscripts Project at the American Museum of Natural History is a scholarly digital initiative that collects, transcribes, and makes accessible Charles Darwin’s scientific manuscripts and related documents online.
E14558 NE FINISHED

How this triple was built (5 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: Darwin Manuscripts Project at the American Museum of Natural History | Statement: [Darwin manuscripts, hasDigitalRepresentation, Darwin Manuscripts Project at the American Museum of Natural History]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Darwin Manuscripts Project at the American Museum of Natural History
Context triple: [Darwin manuscripts, hasDigitalRepresentation, Darwin Manuscripts Project at the American Museum of Natural History]
  • A. Darwin manuscripts
    The Darwin manuscripts are original handwritten notes, drafts, and correspondence by Charles Darwin that document the development of his scientific ideas and theories.
  • B. Darwin Correspondence Project
    The Darwin Correspondence Project is a scholarly initiative that collects, edits, and publishes the letters of Charles Darwin to illuminate his life, work, and scientific networks.
  • C. The Life and Letters of Charles Darwin
    The Life and Letters of Charles Darwin is a biographical collection that interweaves Charles Darwin’s personal correspondence with narrative accounts to illuminate his life, character, and development of his scientific ideas.
  • D. "Emma Darwin: A Century of Family Letters"
    "Emma Darwin: A Century of Family Letters" is a biographical collection of correspondence that offers an intimate portrait of Emma Darwin, her family life, and the Victorian intellectual milieu surrounding Charles Darwin.
  • E. Darwin’s sandwalk
    Darwin’s sandwalk is a tree-lined gravel path near Charles Darwin’s home at Down House in Kent, where he regularly walked while thinking and developing his scientific ideas.
  • 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: Darwin Manuscripts Project at the American Museum of Natural History
Triple: [Darwin manuscripts, hasDigitalRepresentation, Darwin Manuscripts Project at the American Museum of Natural History]
Generated description
The Darwin Manuscripts Project at the American Museum of Natural History is a scholarly digital initiative that collects, transcribes, and makes accessible Charles Darwin’s scientific manuscripts and related documents online.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Darwin Manuscripts Project at the American Museum of Natural History
Target entity description: The Darwin Manuscripts Project at the American Museum of Natural History is a scholarly digital initiative that collects, transcribes, and makes accessible Charles Darwin’s scientific manuscripts and related documents online.
  • A. Darwin manuscripts chosen
    The Darwin manuscripts are original handwritten notes, drafts, and correspondence by Charles Darwin that document the development of his scientific ideas and theories.
  • B. Darwin Correspondence Project
    The Darwin Correspondence Project is a scholarly initiative that collects, edits, and publishes the letters of Charles Darwin to illuminate his life, work, and scientific networks.
  • C. The Life and Letters of Charles Darwin
    The Life and Letters of Charles Darwin is a biographical collection that interweaves Charles Darwin’s personal correspondence with narrative accounts to illuminate his life, character, and development of his scientific ideas.
  • D. "Emma Darwin: A Century of Family Letters"
    "Emma Darwin: A Century of Family Letters" is a biographical collection of correspondence that offers an intimate portrait of Emma Darwin, her family life, and the Victorian intellectual milieu surrounding Charles Darwin.
  • E. Darwin’s sandwalk
    Darwin’s sandwalk is a tree-lined gravel path near Charles Darwin’s home at Down House in Kent, where he regularly walked while thinking and developing his scientific ideas.
  • F. None of above.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasDigitalRepresentation
Context triple: [Darwin manuscripts, hasDigitalRepresentation, Darwin Manuscripts Project at the American Museum of Natural History]
  • A. hasDigitalForm chosen
    Indicates that something exists or is available in a digital or electronic format.
  • B. hasDigitalEncoding
    Indicates that one entity is represented, stored, or expressed using a specific digital code or encoding scheme provided by another entity.
  • C. hasDigitalArchive
    Indicates that an entity maintains or is associated with a collection of materials stored in a digital archive.
  • D. hasDigitalAccess
    Indicates that an entity has the ability or permission to use or access digital resources, services, or information.
  • E. hasDigitalCollections
    Indicates that an entity possesses or provides access to one or more collections of materials in digital form.
  • F. None of above.

Provenance (6 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_69a4934b17c881909ace8270e8ddd202 completed March 1, 2026, 7:28 p.m.
NER Named-entity recognition batch_69a49e41753881909f0faed720cc31bc completed March 1, 2026, 8:14 p.m.
NED1 Entity disambiguation (via context triple) batch_69a567012e9c81909d502e29fff35750 completed March 2, 2026, 10:31 a.m.
NEDg Description generation batch_69a567715b388190849ee0c43380d4be completed March 2, 2026, 10:33 a.m.
NED2 Entity disambiguation (via description) batch_69a567e60de88190a3088e1ada35571c completed March 2, 2026, 10:35 a.m.
PD Predicate disambiguation batch_69a49d0069d0819087c83b608f6fc053 completed March 1, 2026, 8:09 p.m.
Created at: March 1, 2026, 7:35 p.m.