Triple
T18203000
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2021 Czech legislative election |
E435835
|
entity |
| Predicate | coalitionGovernment |
P22392
|
FINISHED |
| Object | SPOLU and PirSTAN |
—
|
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: SPOLU and PirSTAN | Statement: [2021 Czech legislative election, coalitionGovernment, SPOLU and PirSTAN]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: SPOLU and PirSTAN Context triple: [2021 Czech legislative election, coalitionGovernment, SPOLU and PirSTAN]
-
A.
OpenSTEF
OpenSTEF is an open-source project focused on short-term forecasting of electricity demand and generation to support grid reliability and flexibility.
-
B.
SPLS
SPLS is the former NASDAQ stock ticker symbol for Staples Inc., a major American office supplies retail company.
-
C.
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.
-
D.
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.
-
E.
StPO
StPO is the abbreviation for the German Code of Criminal Procedure, which governs how criminal investigations, prosecutions, and trials are conducted in Germany.
- 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: SPOLU and PirSTAN Target entity description: SPOLU and PirSTAN is a Czech political alliance formed by the centre-right SPOLU coalition and the liberal PirSTAN bloc that together challenged Andrej Babiš’s ANO movement in national politics.
-
A.
OpenSTEF
OpenSTEF is an open-source project focused on short-term forecasting of electricity demand and generation to support grid reliability and flexibility.
-
B.
SPLS
SPLS is the former NASDAQ stock ticker symbol for Staples Inc., a major American office supplies retail company.
-
C.
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.
-
D.
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.
-
E.
StPO
StPO is the abbreviation for the German Code of Criminal Procedure, which governs how criminal investigations, prosecutions, and trials are conducted in Germany.
- 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_69e4e220dca48190b54dabbd3c7c99b7 |
completed | April 19, 2026, 2:09 p.m. |
Created at: April 10, 2026, 10:32 a.m.