Triple
T410919
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Józef Piłsudski |
E9487
|
entity |
| Predicate | placeOfBirth |
P1
|
FINISHED |
| Object |
Zułów
Zułów is a village in present-day Lithuania best known as the birthplace of Polish statesman and military leader Józef Piłsudski.
|
E52183
|
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: Zułów | Statement: [Józef Piłsudski, placeOfBirth, Zułów]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Zułów Context triple: [Józef Piłsudski, placeOfBirth, Zułów]
-
A.
Żegota
Żegota was a clandestine Polish World War II organization dedicated to rescuing and aiding Jews under Nazi occupation.
-
B.
Agria
Agria is a coastal town in the Magnesia regional unit of Thessaly, Greece, near the city of Volos.
-
C.
Unternehmen Seelöwe
Unternehmen Seelöwe was Nazi Germany’s planned but never executed World War II invasion of Great Britain in 1940.
-
D.
Count of Vechta
Count of Vechta was a noble title in the Holy Roman Empire associated with the territory around the town of Vechta in present-day Lower Saxony, Germany.
-
E.
Savo
Savo is a town in Kenya’s Central Province known as one of the region’s notable settlements.
- 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: Zułów Triple: [Józef Piłsudski, placeOfBirth, Zułów]
Generated description
Zułów is a village in present-day Lithuania best known as the birthplace of Polish statesman and military leader Józef Piłsudski.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Zułów Target entity description: Zułów is a village in present-day Lithuania best known as the birthplace of Polish statesman and military leader Józef Piłsudski.
-
A.
Żegota
Żegota was a clandestine Polish World War II organization dedicated to rescuing and aiding Jews under Nazi occupation.
-
B.
Agria
Agria is a coastal town in the Magnesia regional unit of Thessaly, Greece, near the city of Volos.
-
C.
Unternehmen Seelöwe
Unternehmen Seelöwe was Nazi Germany’s planned but never executed World War II invasion of Great Britain in 1940.
-
D.
Count of Vechta
Count of Vechta was a noble title in the Holy Roman Empire associated with the territory around the town of Vechta in present-day Lower Saxony, Germany.
-
E.
Savo
Savo is a town in Kenya’s Central Province known as one of the region’s notable settlements.
- 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_69a2e80111fc8190961d5b7c6154123f |
completed | Feb. 28, 2026, 1:05 p.m. |
| NER | Named-entity recognition | batch_69a2ecd96fec8190948fe64928ab4d85 |
completed | Feb. 28, 2026, 1:25 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a41b49b5e48190b7b4a0cc21bb62d5 |
completed | March 1, 2026, 10:56 a.m. |
| NEDg | Description generation | batch_69a41bafe9508190b5e3486bdac5d594 |
completed | March 1, 2026, 10:57 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69a41dabbcf4819084cbe8562d254c2b |
completed | March 1, 2026, 11:06 a.m. |
Created at: Feb. 28, 2026, 1:09 p.m.