Triple
T38345640
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | shogun |
E1041531
|
entity |
| Predicate | formalSuperior |
P30521
|
FINISHED |
| Object | emperor 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: emperor of Japan | Statement: [shogun, formalSuperior, emperor of Japan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: formalSuperior Context triple: [shogun, formalSuperior, emperor of Japan]
-
A.
treatsSuperiors
Indicates how an entity behaves toward or interacts with those in higher-ranking or superior positions.
-
B.
superiorGeneral
Indicates that one entity holds the role or position of superior general in relation to another entity, typically as the highest-ranking leader of a religious order or similar organization.
-
C.
friendAndSuperiorOfficer
Indicates that one person is both a friend of another person and holds a higher-ranking or supervisory position over them.
-
D.
superior
Indicates that one entity holds a higher rank, status, or level of authority than another entity.
-
E.
usedInFormalTitleOf
chosen
Indicates that something is employed as part of the official or formal title of an 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_69f76e2ad95481908c920c0e5c1c3e26 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69fce7671f108190bf3ebf54339068b5 |
completed | May 7, 2026, 7:26 p.m. |
| PD | Predicate disambiguation | batch_69fce5b5a84c81908ac1b5b9f08d48d0 |
completed | May 7, 2026, 7:19 p.m. |
Created at: May 3, 2026, 4:30 p.m.