Triple
T15636969
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | PKT Gdynia |
E375969
|
entity |
| Predicate | shortName |
P43
|
FINISHED |
| Object | PKT Gdynia |
E375969
|
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: PKT Gdynia | Statement: [PKT Gdynia, shortName, PKT Gdynia]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: PKT Gdynia Context triple: [PKT Gdynia, shortName, PKT Gdynia]
-
A.
PKT Gdynia
chosen
PKT Gdynia is a public transport company in Gdynia, Poland, primarily known for running the city’s trolleybus network.
-
B.
Arka Gdynia
Arka Gdynia is a Polish professional football club based in the port city of Gdynia, known for competing in the country’s top leagues and domestic cup competitions.
-
C.
Asseco Gdynia
Asseco Gdynia is a Polish professional basketball club based in Gdynia, known for its success in domestic competitions and participation in European tournaments.
-
D.
Lotos Gdynia
Lotos Gdynia is a Polish professional women's basketball club based in Gdynia that has been one of the country's leading teams in domestic and European competitions.
-
E.
Lechia Gdańsk
Lechia Gdańsk is a Polish professional football club based in Gdańsk, known for competing in the country’s top leagues and having a passionate local fanbase.
- 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_69d85cd035a48190b73d5579ab73969a |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69e04eba51f08190ac5d9de7fc89405a |
completed | April 16, 2026, 2:51 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff5f4923ac8190a03fe1f2c878c27e |
completed | May 9, 2026, 4:22 p.m. |
Created at: April 10, 2026, 4:14 a.m.