Triple
T14781694
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pustynia Błędowska |
E347405
|
entity |
| Predicate | nickname |
P55
|
FINISHED |
| Object | Polish Sahara |
E69644
|
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: Polish Sahara | Statement: [Pustynia Błędowska, nickname, Polish Sahara]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Polish Sahara Context triple: [Pustynia Błędowska, nickname, Polish Sahara]
-
A.
Błędów Desert
chosen
Błędów Desert is a rare inland sand desert in southern Poland, known for its extensive dunes and unique, almost desert-like landscape.
-
B.
Kenji Sahara
Kenji Sahara is a Japanese actor best known for his frequent roles in Toho science fiction and kaiju films, including the Godzilla series.
-
C.
Lommelse Sahara
Lommelse Sahara is a unique Belgian nature reserve known for its expansive sand dunes, pine forests, and scenic lakes that resemble a desert landscape.
-
D.
Saharidj
Saharidj is a town located in Bouira Province in northern Algeria.
-
E.
Burgers' Desert
Burgers' Desert is an indoor desert-themed ecosystem exhibit at Royal Burgers' Zoo in the Netherlands, showcasing flora and fauna from arid regions.
- 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_69d822e9b9e08190bedcc31a163fda82 |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69deca9de3f48190b7706925e2947cf5 |
completed | April 14, 2026, 11:15 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fe0d02e28081909a11d6e6fdb8d28c |
completed | May 8, 2026, 4:19 p.m. |
Created at: April 10, 2026, 1:31 a.m.