Triple
T9185777
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 5th Guards Army |
E220453
|
entity |
| Predicate | roleInBattleOfKursk |
P28183
|
FINISHED |
| Object | Formed part of the strategic reserve |
—
|
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: Formed part of the strategic reserve | Statement: [5th Guards Army, roleInBattleOfKursk, Formed part of the strategic reserve]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: roleInBattleOfKursk Context triple: [5th Guards Army, roleInBattleOfKursk, Formed part of the strategic reserve]
-
A.
roleAtStalingrad
Indicates the specific role, position, or function an entity held in relation to the Battle of Stalingrad.
-
B.
notableBattleRole
chosen
Indicates the specific role or function an entity played in a notable or historically significant battle.
-
C.
worldWarIIRole
Indicates the specific role, position, or function an entity had in relation to World War II.
-
D.
opponentAtStalingrad
Indicates that one entity was an opposing force to another in the context of the Battle of Stalingrad.
-
E.
strategicRoleDuringWar
Indicates that an entity served a particular strategic function or importance during a specific war or armed conflict.
- 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_69ca83e6d77c81909862b7afef56b1bf |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69ccc31a52508190a83ccd76f3aa039b |
completed | April 1, 2026, 7:02 a.m. |
| PD | Predicate disambiguation | batch_69cc66090e5881908889dc1213815626 |
completed | April 1, 2026, 12:25 a.m. |
Created at: March 30, 2026, 7:24 p.m.