Triple
T27932798
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lady Wu |
E708027
|
entity |
| Predicate | motherOfEmperor |
P163788
|
FINISHED |
| Object | Sun Quan |
—
|
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: Sun Quan | Statement: [Lady Wu, motherOfEmperor, Sun Quan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: motherOfEmperor Context triple: [Lady Wu, motherOfEmperor, Sun Quan]
-
A.
predecessorAsMotherOfEmperor
Indicates that one entity is the mother of an emperor and is the immediate predecessor in that maternal role to another such mother.
-
B.
fatherWasEmperorOf
Indicates that the person referred to as the father held the position or title of emperor of the specified entity (such as a state, empire, or territory).
-
C.
successorAsImperialMatriarch
Indicates that one entity becomes the next holder of the role or title of Imperial Matriarch after another entity.
-
D.
marriedToEmperor
Indicates that one entity is the spouse of an emperor, signifying a marital relationship to a reigning or titled emperor.
-
E.
heirMotherOf
Indicates that one entity is the mother of another entity who is designated as an heir.
- 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_69ef96bbf2c48190a9d0e0291457aab6 |
completed | April 27, 2026, 5:02 p.m. |
| NER | Named-entity recognition | batch_69f63c045bd081908e0cb2a119202e8f |
completed | May 2, 2026, 6:01 p.m. |
| PD | Predicate disambiguation | batch_69f6370ea79c81909b761821ee0fa698 |
completed | May 2, 2026, 5:40 p.m. |
| PDg | Predicate description generation | batch_69f63b3039808190b00bbd19161487f3 |
completed | May 2, 2026, 5:58 p.m. |
Created at: April 27, 2026, 7:04 p.m.