Triple

T6991688
Position Surface form Disambiguated ID Type / Status
Subject Thompson's algorithm E162099 entity
Predicate alsoKnownAs P39 FINISHED
Object Thompson construction E162099 NE FINISHED

How this triple was built (2 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: Thompson construction | Statement: [Thompson's algorithm, alsoKnownAs, Thompson construction]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Thompson construction
Context triple: [Thompson's algorithm, alsoKnownAs, Thompson construction]
  • A. Thompson's algorithm for regular expression matching
    Thompson's algorithm for regular expression matching is a classic method that converts regular expressions into nondeterministic finite automata (NFAs) to enable efficient pattern matching in text processing.
  • B. Thompson's algorithm chosen
    Thompson's algorithm is a classic computer science method for converting regular expressions into nondeterministic finite automata (NFAs), widely used in pattern matching and lexical analysis.
  • C. Glushkov construction
    Glushkov construction is a method in automata theory that converts a regular expression into an equivalent nondeterministic finite automaton with a specific position-based structure.
  • D. 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.
  • E. DFA
    DFA is an online advertising management and ad-serving platform originally developed by DoubleClick and later integrated into Google's marketing and ad technology stack.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69c68856d7808190ab33ee914640281b completed March 27, 2026, 1:38 p.m.
NER Named-entity recognition batch_69c6dbc1f63c8190837cfd71cf5ed613 completed March 27, 2026, 7:34 p.m.
NED1 Entity disambiguation (via context triple) batch_69c77551f85881909893d67176ee5556 completed March 28, 2026, 6:29 a.m.
Created at: March 27, 2026, 2:32 p.m.