Triple

T15067383
Position Surface form Disambiguated ID Type / Status
Subject Taiwan Railways network E379789 entity
Predicate connects P390 FINISHED
Object Yunlin E552604 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: Yunlin | Statement: [Taiwan Railways network, connects, Yunlin]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Yunlin
Context triple: [Taiwan Railways network, connects, Yunlin]
  • A. Yunlin County chosen
    Yunlin County is a largely rural county in western Taiwan known for its extensive agricultural production and traditional cultural heritage.
  • B. Chiayi County
    Chiayi County is a largely rural county in southwestern Taiwan known for its agriculture, cultural attractions, and proximity to scenic areas such as Alishan.
  • C. Miaoli County
    Miaoli County is a largely rural county in northwestern Taiwan known for its Hakka cultural heritage, mountainous landscapes, and agricultural communities.
  • D. Hualien County
    Hualien County is a largely mountainous and coastal county on Taiwan’s eastern shore, known for its dramatic Pacific coastline and the famous Taroko Gorge.
  • E. Nantou County
    Nantou County is a mountainous county in central Taiwan known for its indigenous communities, scenic landscapes like Sun Moon Lake, and its role in significant historical events.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d85cd7683881908d405c1b5d7b4f7f completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69dedeea750c819082d8823c9ab6c5a2 completed April 15, 2026, 12:42 a.m.
NED1 Entity disambiguation (via context triple) batch_69fed31debb48190908d59178e67adb6 completed May 9, 2026, 6:24 a.m.
Created at: April 10, 2026, 3:02 a.m.