Triple
T8217612
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Orel salient |
E191974
|
entity |
| Predicate | resultOfOffensive |
P59870
|
FINISHED |
| Object | German withdrawal from Orel area |
—
|
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: German withdrawal from Orel area | Statement: [Orel salient, resultOfOffensive, German withdrawal from Orel area]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: resultOfOffensive Context triple: [Orel salient, resultOfOffensive, German withdrawal from Orel area]
-
A.
offense
Indicates that one entity commits, causes, or is responsible for a violation, wrongdoing, or rule-breaking act against another entity or governing norms.
-
B.
usedOffensiveSystem
Indicates that an entity employed an offensive system (such as a weapon or attack mechanism) against another entity or target.
-
C.
outcomeOf
chosen
Indicates that one entity is the result, consequence, or product that arises from another entity, event, or process.
-
D.
outcomeOffice
Indicates that an outcome or result is associated with, produced by, or realized within a particular office or administrative unit.
-
E.
opposedOutcome
Indicates that one entity’s outcome is in conflict with, counters, or works against the outcome associated with another entity.
- 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_69ca82c9a8ac81908b011c38698456e4 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb776f41108190bed1c6a8ddbea374 |
completed | March 31, 2026, 7:27 a.m. |
| PD | Predicate disambiguation | batch_69cb36ad01ac81909609b15f6a6c8581 |
completed | March 31, 2026, 2:51 a.m. |
Created at: March 30, 2026, 5:45 p.m.