Triple
T28161625
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Duke Xiao of Qin |
E714911
|
entity |
| Predicate | implementedReformsWith |
P75371
|
FINISHED |
| Object | Shang Yang |
—
|
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: Shang Yang | Statement: [Duke Xiao of Qin, implementedReformsWith, Shang Yang]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: implementedReformsWith Context triple: [Duke Xiao of Qin, implementedReformsWith, Shang Yang]
-
A.
implementedReformsIn
Indicates that an entity (typically a person, organization, or government) carried out or put into effect specific reforms within a particular context, domain, or location.
-
B.
reformsBy
chosen
Indicates that one entity initiates, implements, or is responsible for changes or improvements (reforms) affecting another entity.
-
C.
typeOfReforms
Indicates the specific kinds or categories of reforms associated with an entity or situation.
-
D.
associatedReforms
Indicates a relationship where certain reforms are linked or connected to a given entity, such as a policy, event, or individual.
-
E.
survivedReformsOf
Indicates that one entity continued to exist or remain in its role despite reforms, changes, or restructuring initiated by another entity.
- 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_69efd6b156448190bfa15958208395c3 |
completed | April 27, 2026, 9:35 p.m. |
| NER | Named-entity recognition | batch_69f65a6c900881908f18b61273d7bf8d |
completed | May 2, 2026, 8:11 p.m. |
| PD | Predicate disambiguation | batch_69f659ce58408190ba9e007b4810d4d0 |
completed | May 2, 2026, 8:08 p.m. |
Created at: April 27, 2026, 10:06 p.m.