Triple
T14968694
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Działdowo |
E373258
|
entity |
| Predicate | hasSportsClub |
P346
|
FINISHED |
| Object | Start Działdowo |
E373258
|
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: Start Działdowo | Statement: [Działdowo, hasSportsClub, Start Działdowo]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Start Działdowo Context triple: [Działdowo, hasSportsClub, Start Działdowo]
-
A.
Działdowo
chosen
Działdowo is a town in northern Poland known for its historical significance and location within the Warmian-Masurian Voivodeship.
-
B.
Zadwórze
Zadwórze is a village in present-day western Ukraine known primarily as the site of the 1920 Battle of Zadwórze during the Polish–Soviet War.
-
C.
Działoszyce
Działoszyce is a small historic town in south-central Poland, known for its former Jewish community and traditional urban layout.
-
D.
Darłowo
Darłowo is a historic coastal town in northwestern Poland, known for its medieval castle and seaside resort on the Baltic Sea.
-
E.
Gołdap
Gołdap is a town in northeastern Poland known for its spa facilities, scenic lakes and forests, and proximity to the Russian border.
- 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_69d85ccbbcd48190acb56e7cf104d8ad |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69ded6e44cb0819096e09f8026ef8174 |
completed | April 15, 2026, 12:08 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fe8be4b0a88190989022108a58370d |
completed | May 9, 2026, 1:20 a.m. |
Created at: April 10, 2026, 2:48 a.m.