Triple

T11365156
Position Surface form Disambiguated ID Type / Status
Subject UNI Air E269183 entity
Predicate focusCity P164 FINISHED
Object Tainan Airport E282403 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: Tainan Airport | Statement: [UNI Air, focusCity, Tainan Airport]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tainan Airport
Context triple: [UNI Air, focusCity, Tainan Airport]
  • A. Tainan Airport chosen
    Tainan Airport is a regional airport in southern Taiwan serving domestic flights and limited international routes for the city of Tainan.
  • B. Taipei Songshan Airport
    Taipei Songshan Airport is a domestic and regional international airport located near the center of Taipei, Taiwan, serving as a key hub for short-haul flights.
  • C. Taichung International Airport
    Taichung International Airport is a major airport in central Taiwan that serves domestic and international flights and functions as an important regional hub.
  • D. Kaohsiung International Airport
    Kaohsiung International Airport is a major airport in southern Taiwan that serves as an important regional gateway for both domestic and international flights.
  • E. Taitung Airport
    Taitung Airport is a regional airport in southeastern Taiwan that provides domestic flights and connects Taitung County with other major cities and offshore islands.
  • 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_69d6aacca1048190b39dbbc2174616fa completed April 8, 2026, 7:21 p.m.
NER Named-entity recognition batch_69d7ea4589908190948a8225768e1eec completed April 9, 2026, 6:04 p.m.
NED1 Entity disambiguation (via context triple) batch_69e603bbb84c81908a29fcef32d3cf31 completed April 20, 2026, 10:45 a.m.
Created at: April 8, 2026, 9:33 p.m.