Triple
T34953039
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jungmi Treaty |
E1008052
|
entity |
| Predicate | powerAsymmetry |
P86673
|
FINISHED |
| Object | favoring Empire of Japan |
—
|
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: favoring Empire of Japan | Statement: [Jungmi Treaty, powerAsymmetry, favoring Empire of Japan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: powerAsymmetry Context triple: [Jungmi Treaty, powerAsymmetry, favoring Empire of Japan]
-
A.
powerImbalance
chosen
Indicates a relationship where one party holds significantly more power, control, or influence than the other.
-
B.
powerBy
Indicates that one entity operates, functions, or is made possible through the energy, resources, or enabling capabilities provided by another entity.
-
C.
powerPosition
Indicates that one entity holds a position of authority, control, or dominance over another within a hierarchy or power structure.
-
D.
asymmetric
Indicates that the relationship between two entities never holds in both directions simultaneously, so if it holds from A to B it cannot also hold from B to A.
-
E.
powerBalance
Indicates the relative distribution of power or influence between entities in a relationship or interaction.
- 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_69f76dc5d4308190b77553ee07b1ede6 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69fba2877b248190a974eb092243c0c4 |
completed | May 6, 2026, 8:20 p.m. |
| PD | Predicate disambiguation | batch_69fb8d06a1b48190a937aa410d159dfa |
completed | May 6, 2026, 6:48 p.m. |
Created at: May 3, 2026, 4 p.m.