Triple
T22057081
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Środa Wielkopolska |
E545047
|
entity |
| Predicate | historicalName |
P65
|
FINISHED |
| Object |
Środa
Środa is the former name of the Polish town now known as Środa Wielkopolska, located in west-central Poland.
|
E1515087
|
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: Środa | Statement: [Środa Wielkopolska, historicalName, Środa]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Środa Context triple: [Środa Wielkopolska, historicalName, Środa]
-
A.
Çarşamba
Çarşamba is a town and district in Turkey’s Black Sea region, known for its agricultural economy and proximity to the provincial capital Samsun.
-
B.
Wednesday
Wednesday is a professional football club based in Sheffield, England, known as one of the oldest football clubs in the world and a long-time competitor in the English league system.
-
C.
Wednesday
"Wednesday" is a Netflix supernatural comedy-horror series centered on Wednesday Addams as she navigates life at a peculiar boarding school while investigating dark mysteries.
-
D.
Martes
Martes is a genus of small, agile carnivorous mammals in the weasel family that includes martens found across forested regions of the Northern Hemisphere.
-
E.
Dyushambe
Dyushambe is the former name of Dushanbe, the capital and largest city of Tajikistan.
- 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: Środa Triple: [Środa Wielkopolska, historicalName, Środa]
Generated description
Środa is the former name of the Polish town now known as Środa Wielkopolska, located in west-central Poland.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Środa Target entity description: Środa is the former name of the Polish town now known as Środa Wielkopolska, located in west-central Poland.
-
A.
Çarşamba
Çarşamba is a town and district in Turkey’s Black Sea region, known for its agricultural economy and proximity to the provincial capital Samsun.
-
B.
Wednesday
"Wednesday" is a Netflix supernatural comedy-horror series centered on Wednesday Addams as she navigates life at a peculiar boarding school while investigating dark mysteries.
-
C.
Wednesday
Wednesday is a professional football club based in Sheffield, England, known as one of the oldest football clubs in the world and a long-time competitor in the English league system.
-
D.
Martes
Martes is a genus of small, agile carnivorous mammals in the weasel family that includes martens found across forested regions of the Northern Hemisphere.
-
E.
Dyushambe
Dyushambe is the former name of Dushanbe, the capital and largest city of Tajikistan.
- 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_69e11e3377c48190890c17407b9527d6 |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f128588e0081909056ac8251afe935 |
completed | April 28, 2026, 9:36 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0a7b7f1c4c81909d45c8bac72e149b |
completed | May 18, 2026, 2:37 a.m. |
| NEDg | Description generation | batch_6a0a7c8323fc8190b1737d7b85103e98 |
completed | May 18, 2026, 2:42 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0a7d372e30819085fcbbf83a9f5e0a |
completed | May 18, 2026, 2:45 a.m. |
Created at: April 16, 2026, 8:27 p.m.