Triple
T22004268
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lee Jung-gu |
E543407
|
entity |
| Predicate | powerRelationTo |
P144534
|
FINISHED |
| Object | employer of Eun-yi |
—
|
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: employer of Eun-yi | Statement: [Lee Jung-gu, powerRelationTo, employer of Eun-yi]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: powerRelationTo Context triple: [Lee Jung-gu, powerRelationTo, employer of Eun-yi]
-
A.
governingPowerRelationship
Indicates a relationship where one entity holds authoritative control, influence, or ruling power over another entity.
-
B.
relatedPower
Indicates that one entity has a power, authority, or influence that is connected or associated with another entity’s power.
-
C.
powerBy
Indicates that one entity operates, functions, or is made possible through the energy, resources, or enabling capabilities provided by another entity.
-
D.
governingRelation
chosen
Indicates a relationship in which one entity exercises authority, control, or regulatory power over another.
-
E.
powerStructure
Indicates how authority, control, and decision-making are distributed and organized among entities within a system or group.
- 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_69e11e2c814c8190837d072789000486 |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f1276d81e4819083a40e51249e7fd7 |
completed | April 28, 2026, 9:32 p.m. |
| PD | Predicate disambiguation | batch_69e6f62dc9d88190ae387f145f9528de |
completed | April 21, 2026, 3:59 a.m. |
Created at: April 16, 2026, 8:20 p.m.