Triple

T15511903
Position Surface form Disambiguated ID Type / Status
Subject Christopher Manning E368728 entity
Predicate hasTaughtCourse P3295 FINISHED
Object CS124: From Languages to Information
CS124: From Languages to Information is a Stanford University course that introduces students to modern natural language processing and information retrieval techniques at the intersection of computer science and linguistics.
E1160184 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: CS124: From Languages to Information | Statement: [Christopher Manning, hasTaughtCourse, CS124: From Languages to Information]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: CS124: From Languages to Information
Context triple: [Christopher Manning, hasTaughtCourse, CS124: From Languages to Information]
  • A. Texts in Computer Science
    Texts in Computer Science is a scholarly book series that publishes advanced textbooks and monographs across a wide range of computer science topics.
  • B. Department of Language and Computer Science
    The Department of Language and Computer Science is a unit within the Institute of Croatian Language and Linguistics that focuses on the intersection of linguistics and computational methods for language analysis and processing.
  • C. Introduction to the Theory of Computation
    Introduction to the Theory of Computation is a widely used textbook in theoretical computer science that covers formal languages, automata, computability, and complexity theory.
  • D. Programming Language Design and Implementation
    Programming Language Design and Implementation is a premier annual academic conference focusing on research in programming languages and compilers, sponsored by ACM SIGPLAN.
  • E. Information and Computation
    Information and Computation is a peer-reviewed scientific journal focusing on theoretical computer science, including areas such as algorithms, computational complexity, and formal methods.
  • 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: CS124: From Languages to Information
Triple: [Christopher Manning, hasTaughtCourse, CS124: From Languages to Information]
Generated description
CS124: From Languages to Information is a Stanford University course that introduces students to modern natural language processing and information retrieval techniques at the intersection of computer science and linguistics.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: CS124: From Languages to Information
Target entity description: CS124: From Languages to Information is a Stanford University course that introduces students to modern natural language processing and information retrieval techniques at the intersection of computer science and linguistics.
  • A. Texts in Computer Science
    Texts in Computer Science is a scholarly book series that publishes advanced textbooks and monographs across a wide range of computer science topics.
  • B. Department of Language and Computer Science
    The Department of Language and Computer Science is a unit within the Institute of Croatian Language and Linguistics that focuses on the intersection of linguistics and computational methods for language analysis and processing.
  • C. Introduction to the Theory of Computation
    Introduction to the Theory of Computation is a widely used textbook in theoretical computer science that covers formal languages, automata, computability, and complexity theory.
  • D. Programming Language Design and Implementation
    Programming Language Design and Implementation is a premier annual academic conference focusing on research in programming languages and compilers, sponsored by ACM SIGPLAN.
  • E. Information and Computation
    Information and Computation is a peer-reviewed scientific journal focusing on theoretical computer science, including areas such as algorithms, computational complexity, and formal methods.
  • 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_69d85a1794cc8190b0b428716296e63e completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e04030c0208190a1931ea130075603 completed April 16, 2026, 1:49 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff3671a4448190b81edae6ff2669a7 completed May 9, 2026, 1:28 p.m.
NEDg Description generation batch_69ff3725d74081908603d9970857c8b6 completed May 9, 2026, 1:31 p.m.
NED2 Entity disambiguation (via description) batch_69ff37ce835c81909d4538fa4cbfe91f completed May 9, 2026, 1:34 p.m.
Created at: April 10, 2026, 3:56 a.m.