Triple
T28337108
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pei Songzhi |
E717705
|
entity |
| Predicate | annotatedWork |
P4
|
FINISHED |
| Object | Records of the Three Kingdoms |
—
|
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: Records of the Three Kingdoms | Statement: [Pei Songzhi, annotatedWork, Records of the Three Kingdoms]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: annotatedWork Context triple: [Pei Songzhi, annotatedWork, Records of the Three Kingdoms]
-
A.
notableWorkContained
Indicates that a notable work is included within or is part of another entity, such as a collection, publication, or compilation.
-
B.
commentaryWorkFor
Indicates that one entity performs commentary or analysis work on behalf of, or under employment/contract with, another entity.
-
C.
notableWorkBacked
Indicates that a notable work has been supported, endorsed, or financially backed by a particular entity.
-
D.
notableFromWork
Indicates that an entity is notable or well-known specifically because of a particular work it created, contributed to, or is associated with.
-
E.
notableWork
chosen
Indicates that one entity is a significant or well-known work (such as a book, artwork, or creation) produced 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_69eff6e9a57c8190a69c2c74b5d72119 |
completed | April 27, 2026, 11:53 p.m. |
| NER | Named-entity recognition | batch_69f64bd5c8c08190bd5dea179cf08b35 |
completed | May 2, 2026, 7:09 p.m. |
| PD | Predicate disambiguation | batch_69f641e2f1708190b45b48d6a43c51d2 |
completed | May 2, 2026, 6:26 p.m. |
Created at: April 28, 2026, 12:36 a.m.