Triple

T3638023
Position Surface form Disambiguated ID Type / Status
Subject Taipei Songshan Airport E77117 entity
Predicate alternativeName P39 FINISHED
Object Taipei Songshan E77117 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: Taipei Songshan | Statement: [Taipei Songshan Airport, alternativeName, Taipei Songshan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Taipei Songshan
Context triple: [Taipei Songshan Airport, alternativeName, Taipei Songshan]
  • A. Taipei Songshan Airport chosen
    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.
  • B. Xinyi
    Xinyi is a county-level city administered by Xuzhou in Jiangsu Province, eastern China.
  • C. Tainan Airport
    Tainan Airport is a regional airport in southern Taiwan serving domestic flights and limited international routes for the city of Tainan.
  • D. Jiufen
    Jiufen is a historic hillside town in northern Taiwan famed for its narrow lantern-lit streets, teahouses, and scenic views over the Pacific Ocean.
  • E. Tainan
    Tainan is a historic city in southern Taiwan known for its well-preserved temples, traditional culture, and status as the island’s former capital.
  • 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_69ad85dd0be48190b738990cb20c4731 completed March 8, 2026, 2:21 p.m.
NER Named-entity recognition batch_69adc328e5e481909d26318c743bc84a completed March 8, 2026, 6:42 p.m.
NED1 Entity disambiguation (via context triple) batch_69b4c38a70788190908c9a84c7ed7a4f completed March 14, 2026, 2:10 a.m.
Created at: March 8, 2026, 3:24 p.m.