Triple

T1413073
Position Surface form Disambiguated ID Type / Status
Subject Ken Thompson E31846 entity
Predicate thesisTitle P1860 FINISHED
Object Regular Expression Search Algorithm
Regular Expression Search Algorithm is a pattern-matching method for efficiently finding text strings that match specified regular expressions, originally developed and formalized by computer scientist Ken Thompson.
 E162100 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: Regular Expression Search Algorithm | Statement: [Ken Thompson, thesisTitle, Regular Expression Search Algorithm]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Regular Expression Search Algorithm
Context triple: [Ken Thompson, thesisTitle, Regular Expression Search Algorithm]
  • A. Knuth–Morris–Pratt algorithm
    The Knuth–Morris–Pratt algorithm is a classic linear-time string-searching algorithm that efficiently finds occurrences of a pattern within a text by precomputing a prefix function to avoid redundant comparisons.
  • B. GNU Grep
    GNU Grep is the GNU Project’s free, open-source implementation of the grep command-line utility used for fast text searching and pattern matching in files.
  • C. ripgrep
    ripgrep is a fast, command-line search tool written in Rust that recursively searches directories using regular expressions and is widely used as a modern alternative to grep.
  • D. GNU Findutils
    GNU Findutils is a collection of essential GNU utilities, including the widely used `find`, `locate`, `updatedb`, and `xargs` tools, for searching and managing files on Unix-like systems.
  • E. Search and Discovery
    Search and Discovery is a regular Physics Today section that highlights notable recent advances and findings across the physical sciences.
  • 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: Regular Expression Search Algorithm
Triple: [Ken Thompson, thesisTitle, Regular Expression Search Algorithm]
Generated description
Regular Expression Search Algorithm is a pattern-matching method for efficiently finding text strings that match specified regular expressions, originally developed and formalized by computer scientist Ken Thompson.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Regular Expression Search Algorithm
Target entity description: Regular Expression Search Algorithm is a pattern-matching method for efficiently finding text strings that match specified regular expressions, originally developed and formalized by computer scientist Ken Thompson.
  • A. Knuth–Morris–Pratt algorithm
    The Knuth–Morris–Pratt algorithm is a classic linear-time string-searching algorithm that efficiently finds occurrences of a pattern within a text by precomputing a prefix function to avoid redundant comparisons.
  • B. GNU Grep
    GNU Grep is the GNU Project’s free, open-source implementation of the grep command-line utility used for fast text searching and pattern matching in files.
  • C. ripgrep
    ripgrep is a fast, command-line search tool written in Rust that recursively searches directories using regular expressions and is widely used as a modern alternative to grep.
  • D. GNU Findutils
    GNU Findutils is a collection of essential GNU utilities, including the widely used `find`, `locate`, `updatedb`, and `xargs` tools, for searching and managing files on Unix-like systems.
  • E. Search and Discovery
    Search and Discovery is a regular Physics Today section that highlights notable recent advances and findings across the physical sciences.
  • 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_69a49919a994819086528951bc224775 completed March 1, 2026, 7:52 p.m.
NER Named-entity recognition batch_69a4c3e476f08190aed1576805c62462 completed March 1, 2026, 10:55 p.m.
NED1 Entity disambiguation (via context triple) batch_69ace57ec2d88190b06d0f20e3b52462 completed March 8, 2026, 2:57 a.m.
NEDg Description generation batch_69ace5fc91d081909b33009d06a38616 completed March 8, 2026, 2:59 a.m.
NED2 Entity disambiguation (via description) batch_69ace6c10f54819089a4afcf49ef894f completed March 8, 2026, 3:02 a.m.
Created at: March 1, 2026, 7:59 p.m.