Triple
T28106285
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shanghai Higher People’s Court |
E710372
|
entity |
| Predicate | usesSealType |
P40777
|
FINISHED |
| Object | National emblem of the People’s Republic of China on court seal |
—
|
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: National emblem of the People’s Republic of China on court seal | Statement: [Shanghai Higher People’s Court, usesSealType, National emblem of the People’s Republic of China on court seal]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesSealType Context triple: [Shanghai Higher People’s Court, usesSealType, National emblem of the People’s Republic of China on court seal]
-
A.
sealType
chosen
Indicates the specific kind or category of seal associated with an entity or connection.
-
B.
usedSeal
Indicates that an entity has applied or employed a seal (e.g., for closure, authentication, or protection) on another entity.
-
C.
usesSealImage
Indicates that one entity employs or incorporates the seal image of another entity in some context or medium.
-
D.
isSealOf
Indicates that one entity serves as the official seal, emblem, or stamp that authenticates, endorses, or formally represents another entity.
-
E.
isSealed
Indicates that an entity is closed off or secured so that nothing can enter, exit, or be altered.
- 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_69ef9b71fdb081908b4a61cd7ff147c1 |
completed | April 27, 2026, 5:22 p.m. |
| NER | Named-entity recognition | batch_69f7117e55908190a67105e92bc4830f |
completed | May 3, 2026, 9:12 a.m. |
| PD | Predicate disambiguation | batch_69f70f380690819090cc34763ba460ed |
completed | May 3, 2026, 9:02 a.m. |
Created at: April 27, 2026, 9:08 p.m.