Triple

T10057251
Position Surface form Disambiguated ID Type / Status
Subject Wu Zetian E208892 entity
Predicate eraName P2938 FINISHED
Object Tianshou
Tianshou was the brief era name proclaimed by Empress Wu Zetian during her rule in the late 7th century Tang China.
 E838670 NE FINISHED

How this triple was built (4 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: Tianshou | Statement: [Wu Zetian, eraName, Tianshou]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Tianshou
Context triple: [Wu Zetian, eraName, Tianshou]
  • A. Tianshou
    Tianshou is a reinforcement learning library for PyTorch that provides modular, efficient tools and algorithms for training and evaluating RL agents.
  • B. Zhi
    Zhi is a component or subpart of the larger entity or system known as Zhizhong.
  • C. Zheyuan
    Zheyuan is a given name most notably borne by the Chinese general and politician Song Zheyuan.
  • D. Zhiyuan
    Zhiyuan was a late 19th-century protected cruiser of the Qing Dynasty’s Beiyang Fleet, best known for its role and sinking in the First Sino-Japanese War.
  • E. Tianji
    Tianji was the brief final era name used by Sun Hao, the last emperor of Eastern Wu during the late Three Kingdoms period of China.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Tianshou
Triple: [Wu Zetian, eraName, Tianshou]
Generated description
Tianshou was the brief era name proclaimed by Empress Wu Zetian during her rule in the late 7th century Tang China.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Tianshou
Target entity description: Tianshou was the brief era name proclaimed by Empress Wu Zetian during her rule in the late 7th century Tang China.
  • A. Tianshou
    Tianshou is a reinforcement learning library for PyTorch that provides modular, efficient tools and algorithms for training and evaluating RL agents.
  • B. Zhi
    Zhi is a component or subpart of the larger entity or system known as Zhizhong.
  • C. Zheyuan
    Zheyuan is a given name most notably borne by the Chinese general and politician Song Zheyuan.
  • D. Zhiyuan
    Zhiyuan was a late 19th-century protected cruiser of the Qing Dynasty’s Beiyang Fleet, best known for its role and sinking in the First Sino-Japanese War.
  • E. Tianji
    Tianji was the brief final era name used by Sun Hao, the last emperor of Eastern Wu during the late Three Kingdoms period of China.
  • F. None of above. chosen

Provenance (5 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_69ca836094408190a36a1ea7e9a86fcd completed March 30, 2026, 2:06 p.m.
NER Named-entity recognition batch_69cdcfaf7700819084dedf7b63e789c1 completed April 2, 2026, 2:08 a.m.
NED1 Entity disambiguation (via context triple) batch_69d29a5258788190a4ecdefa5b520609 completed April 5, 2026, 5:22 p.m.
NEDg Description generation batch_69d29b7430248190b8965eaf1286dd7c completed April 5, 2026, 5:27 p.m.
NED2 Entity disambiguation (via description) batch_69d29c7ba9f081908f4614098d6c954b completed April 5, 2026, 5:31 p.m.
Created at: March 30, 2026, 8:57 p.m.