Triple
T32368070
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Xi Jinping family |
E827050
|
entity |
| Predicate | hasSpouseFigure |
P33561
|
FINISHED |
| Object | Peng Liyuan |
—
|
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: Peng Liyuan | Statement: [Xi Jinping family, hasSpouseFigure, Peng Liyuan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSpouseFigure Context triple: [Xi Jinping family, hasSpouseFigure, Peng Liyuan]
-
A.
hasSpouseInStory
Indicates that one entity is depicted as the spouse of another within the context of a particular story or narrative.
-
B.
hasPublicFigureSpouse
Indicates that a person’s spouse is a public figure, such as a celebrity, politician, or other widely recognized individual.
-
C.
spouseOfType
Indicates that one entity is the spouse of another, specifying the type or role of that spousal relationship.
-
D.
spouseAssociatedWith
chosen
Indicates a marital or spousal relationship or close association between two entities.
-
E.
spouseCharacterOf
Indicates a marital relationship where one character is the spouse of another character.
- 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_69f349166d548190887b412fe908e2f4 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69fd5d48855c8190bd93070b6a00d8b5 |
completed | May 8, 2026, 3:49 a.m. |
| PD | Predicate disambiguation | batch_69fd5c9aabb88190912800d90184a89d |
completed | May 8, 2026, 3:46 a.m. |
Created at: May 1, 2026, 12:50 a.m.