Triple

T9926767
Position Surface form Disambiguated ID Type / Status
Subject Zhenhai Tower E187941 entity
Predicate ChineseName P744 FINISHED
Object 镇海楼
镇海楼是一座位于中国广州越秀山上的历史性古建筑和地标性城楼,因其观景与防御功能而闻名。
E815748 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: 镇海楼 | Statement: [Zhenhai Tower, ChineseName, 镇海楼]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: 镇海楼
Context triple: [Zhenhai Tower, ChineseName, 镇海楼]
  • A. 春帆楼
    春帆楼 is a historic traditional Japanese restaurant and inn in Shimonoseki, Yamaguchi Prefecture, famed as the site where the Treaty of Shimonoseki was signed.
  • B. 黄鹤楼
    黄鹤楼是位于中国湖北省武汉市长江南岸蛇山之巅的历史名楼,以其悠久的文化底蕴和壮丽的江景闻名于世。
  • C. 城门楼
    城门楼是一种建于城门之上的多层楼阁式建筑,兼具防御、瞭望与礼仪象征等功能,在中国古代城池与宫城中极具代表性。
  • D. 佛香阁
    佛香阁是位于北京颐和园万寿山上的标志性古建筑,也是清代皇家园林中最著名的佛教建筑之一。
  • E. 朝天门
    朝天门 is a historic and iconic riverfront gate area in Chongqing, China, located at the confluence of the Yangtze and Jialing rivers and known today as a major transportation and commercial hub.
  • 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: 镇海楼
Triple: [Zhenhai Tower, ChineseName, 镇海楼]
Generated description
镇海楼是一座位于中国广州越秀山上的历史性古建筑和地标性城楼,因其观景与防御功能而闻名。
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: 镇海楼
Target entity description: 镇海楼是一座位于中国广州越秀山上的历史性古建筑和地标性城楼,因其观景与防御功能而闻名。
  • A. 春帆楼
    春帆楼 is a historic traditional Japanese restaurant and inn in Shimonoseki, Yamaguchi Prefecture, famed as the site where the Treaty of Shimonoseki was signed.
  • B. 黄鹤楼
    黄鹤楼是位于中国湖北省武汉市长江南岸蛇山之巅的历史名楼,以其悠久的文化底蕴和壮丽的江景闻名于世。
  • C. 城门楼 chosen
    城门楼是一种建于城门之上的多层楼阁式建筑,兼具防御、瞭望与礼仪象征等功能,在中国古代城池与宫城中极具代表性。
  • D. 佛香阁
    佛香阁是位于北京颐和园万寿山上的标志性古建筑,也是清代皇家园林中最著名的佛教建筑之一。
  • E. 朝天门
    朝天门 is a historic and iconic riverfront gate area in Chongqing, China, located at the confluence of the Yangtze and Jialing rivers and known today as a major transportation and commercial hub.
  • F. None of above.

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_69ca82b22a688190b52c75bd48429c10 completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cdb59b85f88190899ea279fc02660f completed April 2, 2026, 12:17 a.m.
NED1 Entity disambiguation (via context triple) batch_69d20e1eace88190a591cbab02153869 completed April 5, 2026, 7:24 a.m.
NEDg Description generation batch_69d20ed2dea481909fd9a9dddac3daf1 completed April 5, 2026, 7:27 a.m.
NED2 Entity disambiguation (via description) batch_69d20fef723881909d8d57548461926f completed April 5, 2026, 7:31 a.m.
Created at: March 30, 2026, 8:43 p.m.