Triple
T36370566
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | zwycięstwo Niemiec |
E895740
|
entity |
| Predicate | strona pokonana |
P185732
|
FINISHED |
| Object | Polska |
—
|
NE NERFINISHED |
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: Polska | Statement: [zwycięstwo Niemiec, strona pokonana, Polska]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: strona pokonana Context triple: [zwycięstwo Niemiec, strona pokonana, Polska]
-
A.
finished
Indicates that an entity has completed an action, process, or state, reaching its end point.
-
B.
passed
Indicates that one entity successfully transferred control, responsibility, or an item (such as an object, message, or test) to another entity or through a specified stage or condition.
-
C.
dotyczy
Indicates that something concerns, relates to, or is about a given entity or subject.
-
D.
committed
Indicates that an agent has carried out or been responsible for a specific act, event, or wrongdoing.
-
E.
turnedPro
Indicates that an individual transitioned from amateur status to professional status in a particular field or activity.
- F. None of above. chosen
Provenance (4 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_69f76e5115588190ad8738860b7bc68b |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69f7c371931c8190afb1d4dd5157f92c |
completed | May 3, 2026, 9:51 p.m. |
| PD | Predicate disambiguation | batch_69f7c1b91fd88190ab85afd626603769 |
completed | May 3, 2026, 9:44 p.m. |
| PDg | Predicate description generation | batch_69f7c3705b5c81908c84004543a71c07 |
completed | May 3, 2026, 9:51 p.m. |
Created at: May 3, 2026, 4:10 p.m.