Triple
T28047138
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Liu Sheng, Prince Jing of Zhongshan |
E708714
|
entity |
| Predicate | ancestralLineClaimedBy |
P30356
|
FINISHED |
| Object | Liu Bei |
—
|
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: Liu Bei | Statement: [Liu Sheng, Prince Jing of Zhongshan, ancestralLineClaimedBy, Liu Bei]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ancestralLineClaimedBy Context triple: [Liu Sheng, Prince Jing of Zhongshan, ancestralLineClaimedBy, Liu Bei]
-
A.
lineageClaim
Indicates a claim or assertion that one entity is descended from, or belongs to the ancestral line of, another entity.
-
B.
dynasticClaimBasis
Indicates the basis or grounds on which a person or lineage asserts a dynastic right or claim to rule.
-
C.
allegedAncestor
Indicates that one entity is claimed or suspected to be an ancestor of another, without confirming that the ancestral relationship is true.
-
D.
dynasticClaim
Indicates a relationship where one party asserts a hereditary or lineage-based right to rule, inherit, or hold authority over another.
-
E.
claimedDescentFrom
chosen
Indicates that one entity asserts or maintains that it is descended from, or originates genealogically from, 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_69ef9b6df9f48190bbb971d02cbe1b65 |
completed | April 27, 2026, 5:22 p.m. |
| NER | Named-entity recognition | batch_69f63fd79e4c8190af9263b679e5ff07 |
completed | May 2, 2026, 6:17 p.m. |
| PD | Predicate disambiguation | batch_69f63c6a8474819091b8c6fe98e3862d |
completed | May 2, 2026, 6:03 p.m. |
Created at: April 27, 2026, 8:30 p.m.