Triple
T19955049
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Poland at the Winter Olympic Games |
E479659
|
entity |
| Predicate | notableAthlete |
P10392
|
FINISHED |
| Object |
Karolina Woźniak
Karolina Woźniak is a Polish winter sports athlete who has represented Poland at the Winter Olympic Games.
|
E1405696
|
NE FINISHED |
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: Karolina Woźniak | Statement: [Poland at the Winter Olympic Games, notableAthlete, Karolina Woźniak]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Karolina Woźniak Context triple: [Poland at the Winter Olympic Games, notableAthlete, Karolina Woźniak]
-
A.
Karolina Dąbrowska
Karolina Dąbrowska is a Polish individual notable enough to be recognized as a prominent bearer of the surname Dąbrowska.
-
B.
Katarzyna Michałowska
Katarzyna Michałowska is a researcher known for her scholarly work on Mixe languages, an indigenous language group of Mexico.
-
C.
Joanna Pacuła
Joanna Pacuła is a Polish-born actress and former model best known for her work in American films during the 1980s and 1990s.
-
D.
Katarzyna Nowak
Katarzyna Nowak is a Polish former professional tennis player who was one of Poland’s leading female players in the 1990s.
-
E.
Dagmara Wozniak
Dagmara Wozniak is an American saber fencer and Olympian known for competing internationally for the United States.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Karolina Woźniak Triple: [Poland at the Winter Olympic Games, notableAthlete, Karolina Woźniak]
Generated description
Karolina Woźniak is a Polish winter sports athlete who has represented Poland at the Winter Olympic Games.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Karolina Woźniak Target entity description: Karolina Woźniak is a Polish winter sports athlete who has represented Poland at the Winter Olympic Games.
-
A.
Karolina Dąbrowska
Karolina Dąbrowska is a Polish individual notable enough to be recognized as a prominent bearer of the surname Dąbrowska.
-
B.
Katarzyna Michałowska
Katarzyna Michałowska is a researcher known for her scholarly work on Mixe languages, an indigenous language group of Mexico.
-
C.
Joanna Pacuła
Joanna Pacuła is a Polish-born actress and former model best known for her work in American films during the 1980s and 1990s.
-
D.
Katarzyna Nowak
Katarzyna Nowak is a Polish former professional tennis player who was one of Poland’s leading female players in the 1990s.
-
E.
Dagmara Wozniak
Dagmara Wozniak is an American saber fencer and Olympian known for competing internationally for the United States.
- F. None of above. chosen
Provenance (5 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_69d8e523c19881909f9197037200dde6 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e65aefd9488190b8cdfa8543db8d31 |
completed | April 20, 2026, 4:57 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0804f271288190bc64a89690b3b128 |
completed | May 16, 2026, 5:47 a.m. |
| NEDg | Description generation | batch_6a0806a685b08190b427f32334873661 |
completed | May 16, 2026, 5:54 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a08075f1a48819082f217db39841fdb |
completed | May 16, 2026, 5:57 a.m. |
Created at: April 10, 2026, 1:54 p.m.