Triple
T4063946
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Poland–Soviet Union non-aggression pact |
E86279
|
entity |
| Predicate | terminatedIn |
P29156
|
FINISHED |
| Object | 1939 |
—
|
LITERAL 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: 1939 | Statement: [Poland–Soviet Union non-aggression pact, terminatedIn, 1939]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: terminatedIn Context triple: [Poland–Soviet Union non-aggression pact, terminatedIn, 1939]
-
A.
stoppedAt
Indicates that an entity has come to a halt or pause at a specific location or point in time.
-
B.
terminationCondition
chosen
Indicates the condition or set of conditions under which an ongoing process, activity, or relationship is brought to an end.
-
C.
closedAsTerminal
Indicates that a process, case, or interaction has been concluded in a final, non-reopenable (terminal) state.
-
D.
endedWith
Indicates that one event, process, or state concluded with or was finalized by another specified event, condition, or outcome.
-
E.
terminus
Indicates that one entity serves as the final endpoint or stopping place for another entity’s movement, route, or process.
- F. None of above.
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_69aed93c69208190a4efac0efe3cd69b |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aefd0bdea48190805a79515ee92709 |
completed | March 9, 2026, 5:02 p.m. |
| PD | Predicate disambiguation | batch_69aef90438908190a005b08ba271eacf |
completed | March 9, 2026, 4:44 p.m. |
Created at: March 9, 2026, 3:38 p.m.