Triple
T1570107
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2006 Lebanon War |
E33518
|
entity |
| Predicate | militaryTacticsUsed |
P30685
|
FINISHED |
| Object | air strikes |
—
|
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: air strikes | Statement: [2006 Lebanon War, militaryTacticsUsed, air strikes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: militaryTacticsUsed Context triple: [2006 Lebanon War, militaryTacticsUsed, air strikes]
-
A.
militaryStrategy
Indicates a relationship where an entity plans, directs, or is associated with the organized use of armed forces and tactics to achieve military or defense objectives.
-
B.
militaryUse
Indicates the use of something (such as land, facilities, equipment, or resources) for military purposes or operations.
-
C.
militaryForceUsed
Indicates that one entity employs or applies military power or armed force against, within, or in relation to another entity or situation.
-
D.
militaryDoctrine
Indicates that one entity embodies, follows, or defines the strategic military principles, tactics, and operational guidelines used by another entity.
-
E.
militaryContext
Indicates that the relationship or action occurs within a military setting, framework, or operational environment.
- F. None of above. chosen
Provenance (4 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_69a885f11b048190935025a035302715 |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69a96083e7308190abbf025fe8e43abb |
completed | March 5, 2026, 10:52 a.m. |
| PD | Predicate disambiguation | batch_69a907ba63c88190b60c14dec8d1e40f |
completed | March 5, 2026, 4:34 a.m. |
| PDg | Predicate description generation | batch_69a9607716b4819092187f8c08daaf31 |
completed | March 5, 2026, 10:52 a.m. |
Created at: March 4, 2026, 7:27 p.m.