Triple
T190161
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Paul |
E3700
|
entity |
| Predicate | isCognateOf |
P2527
|
FINISHED |
| Object | Paweł |
E24428
|
NE FINISHED |
How this triple was built (2 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: Paweł | Statement: [Paul, isCognateOf, Paweł]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Paweł Context triple: [Paul, isCognateOf, Paweł]
-
A.
Paweł
chosen
Paweł is a common Polish given name, equivalent to the English name Paul.
-
B.
Piotr
Piotr is the Polish form of the given name Peter, commonly used in Poland and among Polish-speaking communities.
-
C.
Piotr Nowak
Piotr Nowak is a retired Polish attacking midfielder and coach best known for his influential role in Major League Soccer, particularly with the Chicago Fire.
-
D.
Jan Szczepański
Jan Szczepański was a Polish mountaineer known for participating in pioneering high-altitude ascents in the Andes.
-
E.
Wojciech Zaremba
Wojciech Zaremba is a Polish computer scientist and entrepreneur known for co-founding OpenAI and contributing to advances in artificial intelligence research.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69a2548debd48190ae3a06d6e65b53c6 |
completed | Feb. 28, 2026, 2:35 a.m. |
| NER | Named-entity recognition | batch_69a25bc834388190a93ec1ab0d5946de |
completed | Feb. 28, 2026, 3:06 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a31159301481909a3521339d2338fa |
completed | Feb. 28, 2026, 4:01 p.m. |
Created at: Feb. 28, 2026, 2:41 a.m.