Triple
T20257962
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of Hwangsanbeol |
E498752
|
entity |
| Predicate | BaekjeStrategy |
P139427
|
FINISHED |
| Object | defensive stand under General Gyebaek |
—
|
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: defensive stand under General Gyebaek | Statement: [Battle of Hwangsanbeol, BaekjeStrategy, defensive stand under General Gyebaek]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: BaekjeStrategy Context triple: [Battle of Hwangsanbeol, BaekjeStrategy, defensive stand under General Gyebaek]
-
A.
JapaneseTactics
Indicates the use or application of military or strategic methods characteristic of Japanese forces or doctrine.
-
B.
battleStarsKoreanWar
Indicates that an entity received battle stars for its participation in the Korean War.
-
C.
fleetStrategy
Indicates the overarching plan or approach governing how a group of vehicles or vessels is organized, deployed, and operated to achieve specific objectives.
-
D.
JapaneseForceType
Indicates that an entity is classified as a type of Japanese military or armed force.
-
E.
besiegingForce
Indicates a military group that is surrounding and attacking a target location or force in an attempt to capture or subdue it.
- 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_69da6275fa6c8190952924930adee150 |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e674c7296c819092860942de8f28d5 |
completed | April 20, 2026, 6:47 p.m. |
| PD | Predicate disambiguation | batch_69e55b1b23f88190bdcbe2f81dd226dd |
completed | April 19, 2026, 10:45 p.m. |
| PDg | Predicate description generation | batch_69e56702ad04819099c1c08f28d16809 |
completed | April 19, 2026, 11:36 p.m. |
Created at: April 11, 2026, 11:41 p.m.