Triple
T33547502
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Emperor Emeritus of Japan |
E859243
|
entity |
| Predicate | hasCurrentSpouseHolder |
P27098
|
FINISHED |
| Object | Michiko |
—
|
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: Michiko | Statement: [Emperor Emeritus of Japan, hasCurrentSpouseHolder, Michiko]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCurrentSpouseHolder Context triple: [Emperor Emeritus of Japan, hasCurrentSpouseHolder, Michiko]
-
A.
firstHolderSpouseOf
Indicates that the first holder in the relation is the spouse (married partner) of the other holder.
-
B.
thirdHolderSpouse
Indicates that the spouse of the third holder in a sequence or group is related to another specified entity.
-
C.
spouseStatus
Indicates the marital relationship status between two individuals, such as whether they are currently spouses, formerly spouses, or not married to each other.
-
D.
spouseInstanceOf
chosen
Indicates that one entity is the specific spouse (marriage partner) instance of another entity.
-
E.
spouseTermCoincidesWith
Indicates that the term used to refer to a spouse coincides exactly with another specified term in form or usage.
- 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_69f3497a5be08190a39b12736899e034 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69fd864235b481908738dbb69556bc62 |
completed | May 8, 2026, 6:44 a.m. |
| PD | Predicate disambiguation | batch_69fd8373b6bc819091c554f29ee17fec |
completed | May 8, 2026, 6:32 a.m. |
Created at: May 1, 2026, 1:39 a.m.