Triple
T24995282
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of Myeongnyang |
E625550
|
entity |
| Predicate | forceRatio |
P157526
|
FINISHED |
| Object | Joseon fleet heavily outnumbered |
—
|
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: Joseon fleet heavily outnumbered | Statement: [Battle of Myeongnyang, forceRatio, Joseon fleet heavily outnumbered]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: forceRatio Context triple: [Battle of Myeongnyang, forceRatio, Joseon fleet heavily outnumbered]
-
A.
forceDirection
Indicates the direction in which a force is applied or exerted in the relationship between entities.
-
B.
forceSize
Indicates a relationship where one entity specifies or constrains the magnitude or size of a force associated with another entity.
-
C.
forceType
Indicates the specific kind or category of force involved in an interaction or event (e.g., physical, legal, military, or other defined force classifications).
-
D.
forceBalance
Indicates that the net forces acting on an entity or system are in equilibrium, resulting in no overall acceleration.
-
E.
forcesSide2
Indicates that one entity compels or coerces another entity to take or remain on a particular side or position in a situation or conflict.
- 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_69e2ff2611c081908710457fbe6d376b |
completed | April 18, 2026, 3:48 a.m. |
| NER | Named-entity recognition | batch_69f44a4a2c048190bfb5afe6df7ca3f0 |
completed | May 1, 2026, 6:38 a.m. |
| PD | Predicate disambiguation | batch_69f442c0c2e88190acd7f170f10ccef6 |
completed | May 1, 2026, 6:05 a.m. |
| PDg | Predicate description generation | batch_69f448fe11f08190bdd53ca7ba2d51e4 |
completed | May 1, 2026, 6:32 a.m. |
Created at: April 18, 2026, 6:04 a.m.