Triple

T28790874
Position Surface form Disambiguated ID Type / Status
Subject Lin Chuan E726947 entity
Predicate cabinetHeaded P41215 FINISHED
Object Lin Chuan Cabinet
The Lin Chuan Cabinet was the executive administration of Taiwan (Republic of China) led by Premier Lin Chuan, serving under President Tsai Ing-wen after she took office in 2016.
 E1832963 NE FINISHED

How this triple was built (3 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: Lin Chuan Cabinet | Statement: [Lin Chuan, cabinetHeaded, Lin Chuan Cabinet]
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: Lin Chuan Cabinet
Triple: [Lin Chuan, cabinetHeaded, Lin Chuan Cabinet]
Generated description
The Lin Chuan Cabinet was the executive administration of Taiwan (Republic of China) led by Premier Lin Chuan, serving under President Tsai Ing-wen after she took office in 2016.
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: cabinetHeaded
Context triple: [Lin Chuan, cabinetHeaded, Lin Chuan Cabinet]
  • A. cabinetOf chosen
    Indicates that one entity serves as the cabinet or governing body associated with another entity, typically a state, government, or leader.
  • B. hasCabinet
    Indicates that one entity possesses, includes, or is equipped with a cabinet associated with it.
  • C. cabinet
    Indicates that one entity serves as a cabinet (a storage or enclosure unit) for another entity.
  • D. cabinetLevel
    Indicates that an official, position, or body holds a status equivalent to or recognized as part of a national cabinet-level rank or authority.
  • E. cabinetResponsibleTo
    Indicates that a cabinet is politically accountable to, and can be held responsible by, a particular authority or body.
  • F. None of above.

Provenance (6 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_69f0319aabec81908368720196f69a35 completed April 28, 2026, 4:03 a.m.
NER Named-entity recognition batch_69f658ee40088190b71e1219407690d0 completed May 2, 2026, 8:05 p.m.
NED1 Entity disambiguation (via context triple) batch_6a24a27350a08190aee1c682d3226023 completed June 6, 2026, 10:42 p.m.
NEDg Description generation batch_6a24a703ae6c8190b6298c1283e7c9b7 completed June 6, 2026, 11:02 p.m.
NED2 Entity disambiguation (via description) batch_6a24ab4ed6088190a8de9ed2255599ea completed June 6, 2026, 11:20 p.m.
PD Predicate disambiguation batch_69f65760fd3081908ffe014a5e2bf069 completed May 2, 2026, 7:58 p.m.
Created at: April 28, 2026, 6:23 a.m.