Triple

T27807722
Position Surface form Disambiguated ID Type / Status
Subject Hsu Shui-teh as Mayor of Taipei E702428 entity
Predicate officeHeldBy P537 FINISHED
Object Hsu Shui-teh
Hsu Shui-teh is a Taiwanese politician best known for serving as Mayor of Taipei and holding several other key government positions in Taiwan.
E1791882 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: Hsu Shui-teh | Statement: [Hsu Shui-teh as Mayor of Taipei, officeHeldBy, Hsu Shui-teh]
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: Hsu Shui-teh
Triple: [Hsu Shui-teh as Mayor of Taipei, officeHeldBy, Hsu Shui-teh]
Generated description
Hsu Shui-teh is a Taiwanese politician best known for serving as Mayor of Taipei and holding several other key government positions in Taiwan.

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_69ef840a16748190926719ab96120bae completed April 27, 2026, 3:43 p.m.
NER Named-entity recognition batch_69f6383bce8c8190ad97d6bb3bde4175 completed May 2, 2026, 5:45 p.m.
NED1 Entity disambiguation (via context triple) batch_6a12f71e1a148190b6dd6d42d8bf8d1b completed May 24, 2026, 1:03 p.m.
NEDg Description generation batch_6a12fb496c188190abbbcd5200aa5457 completed May 24, 2026, 1:21 p.m.
NED2 Entity disambiguation (via description) batch_6a12fbc87d94819097dbb89898b6ba03 completed May 24, 2026, 1:23 p.m.
Created at: April 27, 2026, 5:40 p.m.