Triple

T17789552
Position Surface form Disambiguated ID Type / Status
Subject Pinglin District E444117 entity
Predicate nearbyTown P3883 FINISHED
Object Yilan City NE NERFINISHED

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: Yilan City | Statement: [Pinglin District, nearbyTown, Yilan City]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Yilan City
Context triple: [Pinglin District, nearbyTown, Yilan City]
  • A. Yilan City chosen
    Yilan City is the county seat and main urban center of Yilan County in northeastern Taiwan, known for its hot springs, coastal scenery, and cultural festivals.
  • B. Hualien City
    Hualien City is a coastal urban center in eastern Taiwan known for its proximity to Taroko Gorge and its role as a regional transportation and tourism hub.
  • C. Pingtung City
    Pingtung City is an urban center in southern Taiwan known as the political and economic hub of Pingtung County.
  • D. Taitung City
    Taitung City is a coastal urban center in southeastern Taiwan known for its indigenous cultures, scenic Pacific shoreline, and role as a gateway to nearby natural attractions and offshore islands.
  • E. Yilan County
    Yilan County is a scenic coastal county in northeastern Taiwan known for its mountains, hot springs, and cultural festivals.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8b9ef17708190bdf7e2adbf14ddc2 completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e4879524bc819090855ab5248c73db completed April 19, 2026, 7:43 a.m.
Created at: April 10, 2026, 10:12 a.m.