Triple

T32008631
Position Surface form Disambiguated ID Type / Status
Subject Kinmen County Council E817338 entity
Predicate meetsAt P373 FINISHED
Object Kinmen County Council building
The Kinmen County Council building is the main governmental facility in Kinmen, Taiwan, serving as the official venue for the county’s legislative and administrative council activities.
E817338 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: Kinmen County Council building | Statement: [Kinmen County Council, meetsAt, Kinmen County Council building]
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: Kinmen County Council building
Triple: [Kinmen County Council, meetsAt, Kinmen County Council building]
Generated description
The Kinmen County Council building is the main governmental facility in Kinmen, Taiwan, serving as the official venue for the county’s legislative and administrative council activities.

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_69f348f9e5d081908cc3f57c4942af52 completed April 30, 2026, 12:20 p.m.
NER Named-entity recognition batch_69f6b42c1bec8190b160b5845b8c03ac completed May 3, 2026, 2:34 a.m.
NED1 Entity disambiguation (via context triple) batch_6a2eb167784481909cf4f9c97ea708c4 completed June 14, 2026, 1:49 p.m.
NEDg Description generation batch_6a2eb233e01081908159fbbd94ad9d22 completed June 14, 2026, 1:52 p.m.
NED2 Entity disambiguation (via description) batch_6a2eb2f4a710819098442ba2198aecf6 completed June 14, 2026, 1:56 p.m.
Created at: May 1, 2026, 12:15 a.m.