Triple
T29592026
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Empress Sunjeonghyo |
E754190
|
entity |
| Predicate | lastEmpressConsortOf |
P167489
|
FINISHED |
| Object | Korea |
—
|
NE NERFINISHED |
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: Korea | Statement: [Empress Sunjeonghyo, lastEmpressConsortOf, Korea]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: lastEmpressConsortOf Context triple: [Empress Sunjeonghyo, lastEmpressConsortOf, Korea]
-
A.
successorAsEmpressDowager
Indicates that one individual becomes the next holder of the title and role of Empress Dowager after another individual.
-
B.
monarchOfConsort
Indicates that one entity is the consort (spouse) of the reigning monarch of another entity (typically a state or territory).
-
C.
successorAsPrimaryEmpressDowager
Indicates that one individual becomes the next holder of the position of primary empress dowager after another, succeeding her in that specific senior imperial consort role.
-
D.
predecessorAsEmpressConsort
Indicates that one empress consort held the position immediately before another empress consort in a succession.
-
E.
successorAsEmpress
Indicates that one person became the next empress following another, directly succeeding her in that imperial role.
- 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_69f0ef836ac88190bd809dc58b5ec907 |
completed | April 28, 2026, 5:33 p.m. |
| NER | Named-entity recognition | batch_69f66db3fdb481909b90ad0a24aaa005 |
completed | May 2, 2026, 9:33 p.m. |
| PD | Predicate disambiguation | batch_69f6659d36208190b01412600a4ed57d |
completed | May 2, 2026, 8:59 p.m. |
| PDg | Predicate description generation | batch_69f6691da93081909deaf680614fc900 |
completed | May 2, 2026, 9:14 p.m. |
Created at: April 28, 2026, 6:15 p.m.