Triple
T31461938
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Emperor Zhi of Han |
E802623
|
entity |
| Predicate | regentClan |
P86707
|
FINISHED |
| Object | Liang clan |
—
|
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 clan | Statement: [Emperor Zhi of Han, regentClan, Liang clan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: regentClan Context triple: [Emperor Zhi of Han, regentClan, Liang clan]
-
A.
rulingClanOf
chosen
Indicates that one clan holds ruling or governing authority over another group, territory, or domain.
-
B.
regentDynasty
Indicates that one entity served as the ruling dynasty or regent house governing on behalf of another entity (such as a realm, monarch, or territory).
-
C.
notableClans
Indicates that there exists a significant or historically important clan associated with the subject.
-
D.
regent
Indicates that one entity serves as the regent, exercising ruling authority on behalf of another (typically a monarch or state), usually during a period when the rightful ruler is unable to govern.
-
E.
regentOf
Indicates a relationship where one entity serves as the ruling authority or caretaker governing on behalf of another entity, typically during the latter’s minority, absence, or incapacity.
- 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_69f348c84c1c81908739f100ecf7394e |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6a5f71b2c8190aade8a83f465be0c |
completed | May 3, 2026, 1:33 a.m. |
| PD | Predicate disambiguation | batch_69f69fe66df08190958558d63ee623d9 |
completed | May 3, 2026, 1:07 a.m. |
Created at: April 30, 2026, 9:20 p.m.