Triple
T25844972
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Former Zhao |
E651040
|
entity |
| Predicate | founderClan |
P152932
|
FINISHED |
| Object | Liu clan of Southern Xiongnu |
—
|
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 clan of Southern Xiongnu | Statement: [Former Zhao, founderClan, Liu clan of Southern Xiongnu]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: founderClan Context triple: [Former Zhao, founderClan, Liu clan of Southern Xiongnu]
-
A.
clanFounder
chosen
Indicates that an entity is the original creator or establisher of a particular clan.
-
B.
clanFamilyOf
Indicates that one entity belongs to, descends from, or is otherwise affiliated with the same clan or extended family group as another entity.
-
C.
clanSocietyFounded
Indicates that a particular clan-based society was established or came into existence at a specified time or by a specified founding event.
-
D.
dominantClanFamilies
Indicates that certain families hold primary power or influence within a clan relative to other families.
-
E.
clanChiefBranchOf
Indicates that a particular clan chief belongs to, or is a leading figure within, a specific branch or subdivision of a larger clan.
- 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_69e7ab38086081908f3a8e7e0c6efd83 |
completed | April 21, 2026, 4:52 p.m. |
| NER | Named-entity recognition | batch_69f6640168948190811bd5f933a87cf5 |
completed | May 2, 2026, 8:52 p.m. |
| PD | Predicate disambiguation | batch_69f6633451948190bcc0410602bb4914 |
completed | May 2, 2026, 8:48 p.m. |
Created at: April 22, 2026, 7:52 a.m.