Triple
T7877816
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Emperor Wen of Han |
E182900
|
entity |
| Predicate | house |
P1505
|
FINISHED |
| Object | Liu family |
E693604
|
NE 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: Liu family | Statement: [Emperor Wen of Han, house, Liu family]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Liu family Context triple: [Emperor Wen of Han, house, Liu family]
-
A.
Liu family
chosen
The Liu family was the imperial clan of the Han dynasty in China, from which emperors such as Guangwu of Han descended.
-
B.
Lin family
The Lin family is a Chinese lineage or clan to which Lin Gie-Ming belongs.
-
C.
Chan family
The Chan family is the family of American pediatrician and philanthropist Priscilla Chan, known in part for its association with major charitable and educational initiatives.
-
D.
Xiong clan
The Xiong clan was the hereditary noble family that provided the kings of the ancient Chinese state of Chu during the Zhou dynasty.
-
E.
Yang clan
The Yang clan is a historically prominent Chinese family lineage known for producing influential military leaders, scholars, and officials across various dynasties.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69ca828a17248190b46defe758bc5ad3 |
completed | March 30, 2026, 2:02 p.m. |
| NER | Named-entity recognition | batch_69cb39bd64e481909f699e7dd2818b8f |
completed | March 31, 2026, 3:04 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cb5b7fef308190bbc74e13f4205192 |
completed | March 31, 2026, 5:28 a.m. |
Created at: March 30, 2026, 4:57 p.m.