Triple
T29969907
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Book of Liang |
E761287
|
entity |
| Predicate | dynastyCovered |
P163952
|
FINISHED |
| Object | Liang dynasty |
—
|
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: Liang dynasty | Statement: [Book of Liang, dynastyCovered, Liang dynasty]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: dynastyCovered Context triple: [Book of Liang, dynastyCovered, Liang dynasty]
-
A.
dynastyProvided
Indicates that a particular dynasty supplied, supported, or was responsible for providing something to another entity or context.
-
B.
dynastyDocumented
chosen
Indicates that a particular dynasty is recorded or attested in some document or documentary source.
-
C.
dynastyDescribedAs
Indicates that a dynasty is characterized or labeled using a particular description, epithet, or qualitative phrase.
-
D.
dynastyInvolved
Indicates that a particular dynasty participates in, is associated with, or plays a role in the referenced event, process, or situation.
-
E.
dynasty
Indicates a hereditary ruling line or family that holds power over a state or territory across successive generations.
- 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_69f22467626081908d5afea489590e96 |
completed | April 29, 2026, 3:31 p.m. |
| NER | Named-entity recognition | batch_69f67f7efc3c8190986d2d95b7a23729 |
completed | May 2, 2026, 10:49 p.m. |
| PD | Predicate disambiguation | batch_69f67e40af9881908de3a4aa15f70a83 |
completed | May 2, 2026, 10:44 p.m. |
Created at: April 29, 2026, 6:31 p.m.