Triple
T7947658
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lu Xun |
E184535
|
entity |
| Predicate | tacticUsedAtYiling |
P30685
|
FINISHED |
| Object | scorched-earth 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: scorched-earth tactics | Statement: [Lu Xun, tacticUsedAtYiling, scorched-earth tactics]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: tacticUsedAtYiling Context triple: [Lu Xun, tacticUsedAtYiling, scorched-earth tactics]
-
A.
tactic
Indicates a strategic method or maneuver employed by one entity to influence, counter, or gain advantage over another in a specific context.
-
B.
tacticsManualUsedBy
Indicates that a tactics manual is utilized or applied by a particular agent or entity.
-
C.
militaryTacticsUsed
chosen
Indicates that specific military tactics are employed or applied in the context of a particular operation, conflict, or strategic situation.
-
D.
tacticalStyle
Indicates the characteristic way in which an entity plans and executes actions or maneuvers to achieve its objectives.
-
E.
hasCommonTacticOfOpponents
Indicates that two or more entities share the same tactic or strategy used by their respective opponents.
- 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_69ca8291c2008190b1b8832c87814bcf |
completed | March 30, 2026, 2:02 p.m. |
| NER | Named-entity recognition | batch_69cb3b2abdbc819085ae53826d36af3b |
completed | March 31, 2026, 3:10 a.m. |
| PD | Predicate disambiguation | batch_69cae9361bc48190886b7681e563d46b |
completed | March 30, 2026, 9:20 p.m. |
Created at: March 30, 2026, 5:09 p.m.