Triple
T88988
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of Iwo Jima |
E1787
|
entity |
| Predicate | defensiveStrategy |
P1135
|
FINISHED |
| Object | Japanese tunnel and bunker system |
—
|
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: Japanese tunnel and bunker system | Statement: [Battle of Iwo Jima, defensiveStrategy, Japanese tunnel and bunker system]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: defensiveStrategy Context triple: [Battle of Iwo Jima, defensiveStrategy, Japanese tunnel and bunker system]
-
A.
defender
Indicates a relationship where one entity protects, guards, or supports another entity against threats, attacks, or criticism.
-
B.
typeOfDefense
chosen
Indicates the specific kind or category of defense employed or possessed in a given context.
-
C.
tactic
Indicates a strategic method or maneuver employed by one entity to influence, counter, or gain advantage over another in a specific context.
-
D.
airDefenseSystemComponent
Indicates that one entity is a component or subsystem of an air defense system associated with another entity.
-
E.
mainAttacker
Indicates that an entity is the primary or leading aggressor responsible for initiating or carrying out an attack against 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_69a24d1a97dc819094e6c021fe9b05a7 |
completed | Feb. 28, 2026, 2:04 a.m. |
| NER | Named-entity recognition | batch_69a24feef1b08190bb9525f71cce053e |
completed | Feb. 28, 2026, 2:16 a.m. |
| PD | Predicate disambiguation | batch_69a24eb82d408190b0f9c786152e8e4c |
completed | Feb. 28, 2026, 2:11 a.m. |
Created at: Feb. 28, 2026, 2:07 a.m.