Triple

T18202979
Position Surface form Disambiguated ID Type / Status
Subject 2021 Czech legislative election E435835 entity
Predicate secondMajorAlliance P130203 FINISHED
Object PirSTAN NE NERFINISHED

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: PirSTAN | Statement: [2021 Czech legislative election, secondMajorAlliance, PirSTAN]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: PirSTAN
Context triple: [2021 Czech legislative election, secondMajorAlliance, PirSTAN]
  • A. PyMC3
    PyMC3 is a Python library for probabilistic programming that enables Bayesian statistical modeling and inference using advanced Markov chain Monte Carlo and variational methods.
  • B. NumPyro
    NumPyro is a lightweight probabilistic programming library for Python that leverages JAX to provide high-performance, scalable Bayesian inference with modern MCMC and variational inference algorithms.
  • C. Hamiltonian Monte Carlo
    Hamiltonian Monte Carlo is an advanced Markov chain Monte Carlo sampling algorithm that uses concepts from Hamiltonian dynamics to efficiently explore complex, high-dimensional probability distributions.
  • D. ArviZ
    ArviZ is an open-source Python library for exploratory analysis and visualization of Bayesian models and probabilistic programming outputs.
  • E. Gibbs sampling
    Gibbs sampling is a Markov chain Monte Carlo algorithm that generates samples from complex multivariate probability distributions by iteratively sampling each variable from its conditional distribution given the others.
  • 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: PirSTAN
Target entity description: PirSTAN was a Czech electoral alliance formed by the Pirate Party and the Mayors and Independents (STAN) to contest national elections with a pro-democratic, pro-European platform.
  • A. PyMC3
    PyMC3 is a Python library for probabilistic programming that enables Bayesian statistical modeling and inference using advanced Markov chain Monte Carlo and variational methods.
  • B. NumPyro
    NumPyro is a lightweight probabilistic programming library for Python that leverages JAX to provide high-performance, scalable Bayesian inference with modern MCMC and variational inference algorithms.
  • C. Hamiltonian Monte Carlo
    Hamiltonian Monte Carlo is an advanced Markov chain Monte Carlo sampling algorithm that uses concepts from Hamiltonian dynamics to efficiently explore complex, high-dimensional probability distributions.
  • D. ArviZ
    ArviZ is an open-source Python library for exploratory analysis and visualization of Bayesian models and probabilistic programming outputs.
  • E. Gibbs sampling
    Gibbs sampling is a Markov chain Monte Carlo algorithm that generates samples from complex multivariate probability distributions by iteratively sampling each variable from its conditional distribution given the others.
  • F. None of above. chosen
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: secondMajorAlliance
Context triple: [2021 Czech legislative election, secondMajorAlliance, PirSTAN]
  • A. majorAllies
    Indicates that the entities are principal or primary allies, signifying a strong, significant, and mutually supportive alliance between them.
  • B. alliesInWar
    Indicates that two or more parties are cooperating as allies on the same side in a specific war or armed conflict.
  • C. mainAlliedPower
    Indicates that an entity serves as a primary or leading ally to another entity within an alliance or coalition.
  • D. historicallyAlliedWith
    Indicates that two entities have been political, military, or strategic allies during some period in the past.
  • E. majorWar
    Indicates a large-scale, intense armed conflict between major powers or involving substantial military forces and widespread impact.
  • F. None of above. chosen

Provenance (4 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_69e4e220dca48190b54dabbd3c7c99b7 completed April 19, 2026, 2:09 p.m.
PD Predicate disambiguation batch_69e4332155d88190b106d0dceb4554af completed April 19, 2026, 1:42 a.m.
PDg Predicate description generation batch_69e438f684e48190b38c64b58c518b6a completed April 19, 2026, 2:07 a.m.
Created at: April 10, 2026, 10:32 a.m.