Triple

T8535483
Position Surface form Disambiguated ID Type / Status
Subject 1890 United States Census E202066 entity
Predicate innovator P83191 FINISHED
Object Herman Hollerith
Herman Hollerith was an American inventor and statistician best known for developing the punched-card tabulating machines that revolutionized data processing and led to the formation of IBM.
E740626 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: Herman Hollerith | Statement: [1890 United States Census, innovator, Herman Hollerith]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Herman Hollerith
Context triple: [1890 United States Census, innovator, Herman Hollerith]
  • A. Howard Aiken
    Howard Aiken was an American engineer and computing pioneer best known for designing the IBM Harvard Mark I, one of the earliest large-scale automatic digital computers.
  • B. Allan W. Eckert
    Allan W. Eckert was an American author and naturalist best known for his meticulously researched historical novels and nature writing, including the "Winning of America" series.
  • C. Wallace John Eckert
    Wallace John Eckert was an American astronomer and pioneer of computational methods who used early punched-card and electronic computers to advance celestial mechanics and navigation.
  • D. Theodore Case
    Theodore Case was an American inventor and pioneer of sound-on-film technology whose work helped enable synchronized audio in motion pictures.
  • E. William Cocke
    William Cocke was an early American frontiersman, Revolutionary War soldier, and politician who served as one of Tennessee’s first U.S. senators.
  • 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: Herman Hollerith
Triple: [1890 United States Census, innovator, Herman Hollerith]
Generated description
Herman Hollerith was an American inventor and statistician best known for developing the punched-card tabulating machines that revolutionized data processing and led to the formation of IBM.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Herman Hollerith
Target entity description: Herman Hollerith was an American inventor and statistician best known for developing the punched-card tabulating machines that revolutionized data processing and led to the formation of IBM.
  • A. Howard Aiken
    Howard Aiken was an American engineer and computing pioneer best known for designing the IBM Harvard Mark I, one of the earliest large-scale automatic digital computers.
  • B. Allan W. Eckert
    Allan W. Eckert was an American author and naturalist best known for his meticulously researched historical novels and nature writing, including the "Winning of America" series.
  • C. Wallace John Eckert
    Wallace John Eckert was an American astronomer and pioneer of computational methods who used early punched-card and electronic computers to advance celestial mechanics and navigation.
  • D. Theodore Case
    Theodore Case was an American inventor and pioneer of sound-on-film technology whose work helped enable synchronized audio in motion pictures.
  • E. William Cocke
    William Cocke was an early American frontiersman, Revolutionary War soldier, and politician who served as one of Tennessee’s first U.S. senators.
  • F. None of above. chosen
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: innovator
Context triple: [1890 United States Census, innovator, Herman Hollerith]
  • A. innovation
    Indicates the introduction or development of something new or significantly improved compared to existing methods, products, or ideas.
  • B. innovationFrom
    Indicates that something originates, arises, or is derived as an innovation from a particular source or prior entity.
  • C. founder
    Indicates that an entity established, created, or started another entity such as an organization, institution, or company.
  • D. initiator
    Indicates the entity that starts, triggers, or causes an action, event, or process to occur.
  • E. visionaryOf
    Indicates that one entity is the original conceiver or driving visionary behind the creation, direction, or concept of another entity.
  • F. None of above. chosen

Provenance (7 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_69ca832355b08190b8b6a4ab4a4a3554 completed March 30, 2026, 2:05 p.m.
NER Named-entity recognition batch_69cbe6a295c88190a432a060ee73f04e completed March 31, 2026, 3:22 p.m.
NED1 Entity disambiguation (via context triple) batch_69ce6d8332cc819083c86e0dc58bcc37 completed April 2, 2026, 1:22 p.m.
NEDg Description generation batch_69ce6f02fabc819093b95e0d318c5649 completed April 2, 2026, 1:28 p.m.
NED2 Entity disambiguation (via description) batch_69ce6f9b12148190be55b3f5f2b518d9 completed April 2, 2026, 1:31 p.m.
PD Predicate disambiguation batch_69cbd111bf988190be98c92a607c6456 completed March 31, 2026, 1:50 p.m.
PDg Predicate description generation batch_69cbe30d453481908f897ed2b06e7534 completed March 31, 2026, 3:06 p.m.
Created at: March 30, 2026, 6:17 p.m.