Triple
T29656773
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mongolia–Manchukuo border |
E750288
|
entity |
| Predicate | belligerentsAtKhalkhinGol |
P79025
|
FINISHED |
| Object | Soviet Union |
—
|
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: Soviet Union | Statement: [Mongolia–Manchukuo border, belligerentsAtKhalkhinGol, Soviet Union]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: belligerentsAtKhalkhinGol Context triple: [Mongolia–Manchukuo border, belligerentsAtKhalkhinGol, Soviet Union]
-
A.
battlesWith
Indicates that two entities are engaged in active conflict, combat, or struggle against each other.
-
B.
battleBelligerentAtSite
chosen
Indicates that a particular belligerent (participant in a battle) was present and engaged in that battle at a specified site or location.
-
C.
battlefieldOf
Indicates that a location is the site where a particular battle or military engagement took place.
-
D.
sideInRussianCivilWar
Indicates the faction or side that an entity supported or belonged to during the Russian Civil War.
-
E.
battleInvolvedIn
Indicates that an entity participated as a combatant or directly took part in a specific battle or military engagement.
- 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_69f0d6226fe881908819197c9ef9ee04 |
completed | April 28, 2026, 3:45 p.m. |
| NER | Named-entity recognition | batch_69f66f2850288190a394272ae49084e3 |
completed | May 2, 2026, 9:39 p.m. |
| PD | Predicate disambiguation | batch_69f6659f246081909821c5f452d14e8f |
completed | May 2, 2026, 8:59 p.m. |
Created at: April 28, 2026, 6:55 p.m.