Triple
T30192198
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Empress Xiaozhaoren |
E767520
|
entity |
| Predicate | banner |
P131297
|
FINISHED |
| Object | Plain Yellow Banner |
—
|
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: Plain Yellow Banner | Statement: [Empress Xiaozhaoren, banner, Plain Yellow Banner]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: banner Context triple: [Empress Xiaozhaoren, banner, Plain Yellow Banner]
-
A.
bannerType
Indicates the specific category or style of a banner associated with an entity or context.
-
B.
bannerColor
Indicates the color associated with a banner in the relationship or context described.
-
C.
badge
Indicates that one entity confers, displays, or is associated with a symbolic mark or emblem representing status, achievement, role, or affiliation in relation to another entity.
-
D.
bannerAffiliation
chosen
Indicates that an entity is associated with, represented by, or operating under a particular banner, label, or identifying heading.
-
E.
brand
Indicates that one entity is the commercial brand or label under which another entity (such as a product, service, or organization) is marketed or identified.
- 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_69f2247db1108190835c0727c97637c3 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f67f84b03c8190a2574fde91d86e8c |
completed | May 2, 2026, 10:49 p.m. |
| PD | Predicate disambiguation | batch_69f673c7a4588190837854f3ef61e6bf |
completed | May 2, 2026, 9:59 p.m. |
Created at: April 29, 2026, 7:29 p.m.