Triple
T20566357
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zilu |
E504974
|
entity |
| Predicate | contrastedWith |
P278
|
FINISHED |
| Object | Yan Hui |
—
|
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: Yan Hui | Statement: [Zilu, contrastedWith, Yan Hui]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Yan Hui Context triple: [Zilu, contrastedWith, Yan Hui]
-
A.
Yan Hui
chosen
Yan Hui was Confucius’s favorite disciple, renowned for his exceptional virtue, humility, and understanding of Confucian teachings.
-
B.
Zigong
Zigong is a historic industrial city in southern Sichuan, China, best known for its ancient salt industry and renowned dinosaur fossil sites.
-
C.
Zengzi
Zengzi was a prominent disciple of Confucius, renowned for his moral integrity and influential role in the development and transmission of Confucian thought.
-
D.
Junzi
Junzi is a central Confucian ideal of the morally exemplary "gentleman" or noble person who embodies virtue, righteousness, and proper conduct.
-
E.
Zhongyong
Zhongyong is a classical Confucian text that expounds the ideal of moral moderation, balance, and harmony as a central path to personal virtue and good governance.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0b4b6587c8190aee63dc7cff244ea |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6a7a228948190b47a3a61f239e00d |
completed | April 20, 2026, 10:24 p.m. |
Created at: April 16, 2026, 11:39 a.m.