Triple

T15661399
Position Surface form Disambiguated ID Type / Status
Subject RCTP E376573 entity
Predicate focusCityFor P164 FINISHED
Object Starlux Airlines E925488 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: Starlux Airlines | Statement: [RCTP, focusCityFor, Starlux Airlines]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Starlux Airlines
Context triple: [RCTP, focusCityFor, Starlux Airlines]
  • A. Starlux Airlines chosen
    Starlux Airlines is a Taiwanese full-service carrier based in Taipei, known for its premium cabins and stylish branding on regional and long-haul routes in Asia and beyond.
  • B. Gulf Air
    Gulf Air is the national flag carrier airline of the Kingdom of Bahrain, operating regional and international flights across the Middle East, Asia, Europe, and Africa.
  • C. Iraqi Airways
    Iraqi Airways is the national flag carrier airline of Iraq, operating domestic and international passenger and cargo services across the Middle East, Europe, and other regions.
  • D. Nile Air
    Nile Air is a privately owned Egyptian airline that operates domestic and regional flights across the Middle East, North Africa, and parts of Europe.
  • E. Jazeera Airways
    Jazeera Airways is a Kuwaiti low-cost airline based in Kuwait that operates regional and international flights across the Middle East, Asia, and Europe.
  • 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_69d85cd1564c8190991adda63bfab4b0 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e04ef4e6a08190ad8bbafaa3612f22 completed April 16, 2026, 2:52 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff679e0f2c8190bbcb7051c38e1580 completed May 9, 2026, 4:58 p.m.
Created at: April 10, 2026, 4:15 a.m.