Triple
T24485236
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Imperial Austrian Army |
E617485
|
entity |
| Predicate | standardTactic |
P1716
|
FINISHED |
| Object | linear infantry tactics |
—
|
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: linear infantry tactics | Statement: [Imperial Austrian Army, standardTactic, linear infantry tactics]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: standardTactic Context triple: [Imperial Austrian Army, standardTactic, linear infantry tactics]
-
A.
tactic
chosen
Indicates a strategic method or maneuver employed by one entity to influence, counter, or gain advantage over another in a specific context.
-
B.
standardApproach
Indicates that an entity uses or follows a commonly accepted, conventional, or typical method for addressing a task or problem.
-
C.
standardUse
Indicates that something is used in a typical, expected, or officially accepted manner for its intended purpose.
-
D.
standardPar
Indicates that two entities are parallel and conform to a recognized or defined standard of parallelism.
-
E.
standardType
Indicates that one entity is classified as the standard, canonical, or reference type for another entity or context.
- 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_69e2d7f3ae788190b683394db15f220e |
completed | April 18, 2026, 1:01 a.m. |
| NER | Named-entity recognition | batch_69f2a9d912e88190bc39c05a9d7f407e |
completed | April 30, 2026, 1:01 a.m. |
| PD | Predicate disambiguation | batch_69f2a6a4580481908fddc385f5262f95 |
completed | April 30, 2026, 12:47 a.m. |
Created at: April 18, 2026, 2:21 a.m.