Triple

T18200388
Position Surface form Disambiguated ID Type / Status
Subject Judea Pearl E435765 entity
Predicate knownFor P22 FINISHED
Object do-calculus NE NERFINISHED

How this triple was built (3 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: do-calculus | Statement: [Judea Pearl, knownFor, do-calculus]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: do-calculus
Context triple: [Judea Pearl, knownFor, do-calculus]
  • A. Causal Inference for Statistics, Social, and Biomedical Sciences
    "Causal Inference for Statistics, Social, and Biomedical Sciences" is a foundational textbook that systematically develops modern methods for drawing causal conclusions from data in fields such as statistics, social science, and biomedicine.
  • B. Rubin causal model
    The Rubin causal model is a foundational framework in statistics and causal inference that defines causal effects through comparisons of potential outcomes under different treatments or interventions.
  • C. “Statistical Confluence Analysis by Means of Complete Regression Systems”
    “Statistical Confluence Analysis by Means of Complete Regression Systems” is a foundational econometric work by Ragnar Frisch that develops a systematic regression-based framework for analyzing interdependent economic relationships.
  • D. Bayesian networks
    Bayesian networks are probabilistic graphical models that represent variables and their conditional dependencies using directed acyclic graphs, enabling structured reasoning and inference under uncertainty.
  • E. The Theory of Confounding
    The Theory of Confounding is a foundational chapter in R.A. Fisher’s work on experimental design that explains how to manage and interpret the mixing of treatment effects with nuisance factors in statistical experiments.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: do-calculus
Target entity description: Do-calculus is a set of mathematical rules developed by Judea Pearl for identifying causal effects from probabilistic models and observational data.
  • A. Causal Inference for Statistics, Social, and Biomedical Sciences
    "Causal Inference for Statistics, Social, and Biomedical Sciences" is a foundational textbook that systematically develops modern methods for drawing causal conclusions from data in fields such as statistics, social science, and biomedicine.
  • B. Rubin causal model
    The Rubin causal model is a foundational framework in statistics and causal inference that defines causal effects through comparisons of potential outcomes under different treatments or interventions.
  • C. “Statistical Confluence Analysis by Means of Complete Regression Systems”
    “Statistical Confluence Analysis by Means of Complete Regression Systems” is a foundational econometric work by Ragnar Frisch that develops a systematic regression-based framework for analyzing interdependent economic relationships.
  • D. Bayesian networks
    Bayesian networks are probabilistic graphical models that represent variables and their conditional dependencies using directed acyclic graphs, enabling structured reasoning and inference under uncertainty.
  • E. The Theory of Confounding
    The Theory of Confounding is a foundational chapter in R.A. Fisher’s work on experimental design that explains how to manage and interpret the mixing of treatment effects with nuisance factors in statistical experiments.
  • F. None of above. chosen

Provenance (2 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_69d8b90dba6481908e119eb9aa4ca0cb completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4e0d610f88190b4f69b1c433ea6b1 completed April 19, 2026, 2:04 p.m.
Created at: April 10, 2026, 10:31 a.m.