Triple

T21950185
Position Surface form Disambiguated ID Type / Status
Subject Qi E542044 entity
Predicate founder P104 FINISHED
Object Jiang Ziya 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: Jiang Ziya | Statement: [Qi, founder, Jiang Ziya]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jiang Ziya
Context triple: [Qi, founder, Jiang Ziya]
  • A. Jiang Ziya chosen
    Jiang Ziya is a legendary Chinese strategist and statesman of the late Shang and early Zhou dynasties, famed for helping King Wen and King Wu overthrow the Shang and establish the Zhou dynasty.
  • B. Li Shang
    Li Shang is a disciplined and honorable Chinese army captain who becomes Mulan’s commanding officer and eventual love interest in Disney’s animated film "Mulan."
  • C. Tao Zhu Gong
    Tao Zhu Gong, also known as Fan Li, was an ancient Chinese strategist and statesman who later became a legendary merchant and is often revered as a patron saint of business and commerce.
  • D. Cheng Tang
    Cheng Tang was the founding king of China's Shang dynasty, renowned for toppling the Xia dynasty and establishing a new ruling order.
  • E. Shen Dao
    Shen Dao is the ceremonial spirit road leading to the Ming Tombs near Beijing, lined with stone statues and monuments that honor deceased emperors.
  • 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_69e0c47ef0e48190a50e1bcc43f4b3fd completed April 16, 2026, 11:14 a.m.
NER Named-entity recognition batch_69f1243bb9c88190a3774b9fa2af9871 completed April 28, 2026, 9:18 p.m.
Created at: April 16, 2026, 7:58 p.m.