Triple
T26369223
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Liu Song |
E660724
|
entity |
| Predicate | ethnicBaseOfRulingHouse |
P167284
|
FINISHED |
| Object | Han Chinese |
—
|
LITERAL FINISHED |
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: Han Chinese | Statement: [Liu Song, ethnicBaseOfRulingHouse, Han Chinese]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ethnicBaseOfRulingHouse Context triple: [Liu Song, ethnicBaseOfRulingHouse, Han Chinese]
-
A.
rulingHouse
Indicates that one entity serves as the dynastic or noble family that holds ruling authority over another entity, such as a state, territory, or polity.
-
B.
foundingHouse
Indicates that one entity is the original ruling family, dynasty, or lineage that established or founded another entity (such as a state, organization, or institution).
-
C.
monarchicalHouse
Indicates that an entity belongs to, is associated with, or is part of a particular royal or monarchical house or dynasty.
-
D.
crownedMonarchHouse
Indicates that a particular royal house is the one from which a given monarch was crowned or to which that crowned monarch belongs.
-
E.
formerRulerHouse
Indicates that a person once ruled on behalf of, or as a member of, a particular ruling house or dynasty but no longer holds that ruling position.
- 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_69ee812a698881908d6a58265995fa39 |
completed | April 26, 2026, 9:18 p.m. |
| NER | Named-entity recognition | batch_69f66a6468ec8190a43ed6cd8c797f42 |
completed | May 2, 2026, 9:19 p.m. |
| PD | Predicate disambiguation | batch_69f66598d6008190a7ca8ff80399fd34 |
completed | May 2, 2026, 8:59 p.m. |
| PDg | Predicate description generation | batch_69f6691da93081909deaf680614fc900 |
completed | May 2, 2026, 9:14 p.m. |
Created at: April 26, 2026, 10:57 p.m.