Triple
T28459588
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Emperor Shenzong of Song |
E720112
|
entity |
| Predicate | supportedReformer |
P202651
|
FINISHED |
| Object | Wang Anshi |
—
|
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: Wang Anshi | Statement: [Emperor Shenzong of Song, supportedReformer, Wang Anshi]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportedReformer Context triple: [Emperor Shenzong of Song, supportedReformer, Wang Anshi]
-
A.
supportsReformType
Indicates that one entity endorses, advocates for, or is in favor of a particular type or category of reform associated with another entity.
-
B.
reformedWithSupportFrom
Indicates that an entity underwent reform or significant change with the assistance, backing, or encouragement of another entity.
-
C.
reformerOf
Indicates that one entity is the person or agent who initiated or carried out significant reforms or changes to another entity.
-
D.
supportsForm
Indicates that one entity provides compatibility or backing for a particular form, format, or type associated with another entity.
-
E.
supportedAmendment
Indicates that one entity endorsed, backed, or voted in favor of a particular amendment.
- 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_69f01a58a67c819097936d9e8da8d6e6 |
completed | April 28, 2026, 2:24 a.m. |
| NER | Named-entity recognition | batch_6a00a74c0564819081e1c4c29b9d0d15 |
completed | May 10, 2026, 3:42 p.m. |
| PD | Predicate disambiguation | batch_6a00a6a63ef48190a743c88534d9d672 |
completed | May 10, 2026, 3:39 p.m. |
| PDg | Predicate description generation | batch_6a00a74afb3c8190a274bf6681950aa3 |
completed | May 10, 2026, 3:42 p.m. |
Created at: April 28, 2026, 2:38 a.m.