Triple
T31521223
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kim So-yeon |
E804208
|
entity |
| Predicate | spouseNumberForGerhardSchroeder |
P143394
|
FINISHED |
| Object | fifth wife |
—
|
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: fifth wife | Statement: [Kim So-yeon, spouseNumberForGerhardSchroeder, fifth wife]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: spouseNumberForGerhardSchroeder Context triple: [Kim So-yeon, spouseNumberForGerhardSchroeder, fifth wife]
-
A.
spouseOfOfficeholderNumber
Indicates that one entity is the spouse of a specific officeholder identified by their ordinal number in holding a particular office.
-
B.
spouseNumberOfTermsInOffice
Indicates the number of distinct terms in office that the spouse of the referenced entity has served.
-
C.
spouseCountIncludes
chosen
Indicates that the recorded count of spouses for an entity includes the referenced spouse or spouses within that total.
-
D.
spouseCount
Indicates the number of spouses an entity has.
-
E.
spouseCountWith
Indicates the number of spouses an entity has in relation to another specified entity or context.
- 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_69f348cf839c81908657048402f7f97b |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69fd4f39b5008190b83b3227ce22c509 |
completed | May 8, 2026, 2:49 a.m. |
| PD | Predicate disambiguation | batch_69fd4df17c548190a4e2a6fea70f7e10 |
completed | May 8, 2026, 2:44 a.m. |
Created at: April 30, 2026, 9:56 p.m.