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.