Triple

T15066710
Position Surface form Disambiguated ID Type / Status
Subject Edward D. Lazowska E379773 entity
Predicate notableWork P4 FINISHED
Object Leadership in data-intensive discovery and eScience initiatives
"Leadership in data-intensive discovery and eScience initiatives" is a prominent work by computer scientist Edward D. Lazowska that highlights and advances the role of large-scale data and computational methods in modern scientific research.
E1134679 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: Leadership in data-intensive discovery and eScience initiatives | Statement: [Edward D. Lazowska, notableWork, Leadership in data-intensive discovery and eScience initiatives]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Leadership in data-intensive discovery and eScience initiatives
Context triple: [Edward D. Lazowska, notableWork, Leadership in data-intensive discovery and eScience initiatives]
  • A. Data-Driven Discovery Initiative
    The Data-Driven Discovery Initiative is a research program that advances scientific discovery by supporting innovative data science methods, tools, and researchers across disciplines.
  • B. Scientific Data Systems
    Scientific Data Systems was an early computer company known for producing advanced scientific and real-time computing systems in the 1960s before being acquired by Xerox.
  • C. Digital Science
    Digital Science is a technology company that provides research analytics, data, and software tools to support and improve the scholarly research ecosystem.
  • D. Community Science and Data Center
    The Community Science and Data Center is a facility that provides data services, tools, and support to enable broad community access to astronomical observations and research.
  • E. Worldwide LHC Computing Grid
    The Worldwide LHC Computing Grid is a global distributed computing infrastructure that processes, stores, and analyzes the vast amounts of data produced by the Large Hadron Collider experiments.
  • 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: Leadership in data-intensive discovery and eScience initiatives
Triple: [Edward D. Lazowska, notableWork, Leadership in data-intensive discovery and eScience initiatives]
Generated description
"Leadership in data-intensive discovery and eScience initiatives" is a prominent work by computer scientist Edward D. Lazowska that highlights and advances the role of large-scale data and computational methods in modern scientific research.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Leadership in data-intensive discovery and eScience initiatives
Target entity description: "Leadership in data-intensive discovery and eScience initiatives" is a prominent work by computer scientist Edward D. Lazowska that highlights and advances the role of large-scale data and computational methods in modern scientific research.
  • A. Data-Driven Discovery Initiative
    The Data-Driven Discovery Initiative is a research program that advances scientific discovery by supporting innovative data science methods, tools, and researchers across disciplines.
  • B. Scientific Data Systems
    Scientific Data Systems was an early computer company known for producing advanced scientific and real-time computing systems in the 1960s before being acquired by Xerox.
  • C. Digital Science
    Digital Science is a technology company that provides research analytics, data, and software tools to support and improve the scholarly research ecosystem.
  • D. Community Science and Data Center
    The Community Science and Data Center is a facility that provides data services, tools, and support to enable broad community access to astronomical observations and research.
  • E. Worldwide LHC Computing Grid
    The Worldwide LHC Computing Grid is a global distributed computing infrastructure that processes, stores, and analyzes the vast amounts of data produced by the Large Hadron Collider experiments.
  • 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_69d85cd7683881908d405c1b5d7b4f7f completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69dedeea750c819082d8823c9ab6c5a2 completed April 15, 2026, 12:42 a.m.
NED1 Entity disambiguation (via context triple) batch_69fea5cb04e88190a42bb0e516df61bc completed May 9, 2026, 3:11 a.m.
NEDg Description generation batch_69fea66a04988190b483210c1671d287 completed May 9, 2026, 3:13 a.m.
NED2 Entity disambiguation (via description) batch_69fea70e2fbc81908f168925b06bdbd6 completed May 9, 2026, 3:16 a.m.
Created at: April 10, 2026, 3:02 a.m.