Triple

T7471699
Position Surface form Disambiguated ID Type / Status
Subject Kish International Airport E176521 entity
Predicate servesAirline P12356 FINISHED
Object Caspian Airlines E201962 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: Caspian Airlines | Statement: [Kish International Airport, servesAirline, Caspian Airlines]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Caspian Airlines
Context triple: [Kish International Airport, servesAirline, Caspian Airlines]
  • A. Caspian Airlines chosen
    Caspian Airlines is an Iranian passenger airline operating domestic and regional flights, with a primary hub at Tehran Imam Khomeini International Airport.
  • B. Iran Aseman Airlines
    Iran Aseman Airlines is an Iranian airline headquartered in Tehran that operates domestic and regional flights across the Middle East and surrounding regions.
  • C. Palestine Airways
    Palestine Airways was an early commercial airline that operated in the British Mandate of Palestine in the 1930s, providing regional passenger and mail services in the Eastern Mediterranean.
  • D. Alia Airlines
    Alia Airlines was the original name of Royal Jordanian, the flag carrier airline of Jordan.
  • E. Karun Airlines
    Karun Airlines is an Iranian airline that operates passenger and cargo services, primarily based in Tehran.
  • 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_69c69f223fd88190b4c69b95d7cbeeda completed March 27, 2026, 3:15 p.m.
NER Named-entity recognition batch_69c6f415b5cc81909e1e097c90f460b6 completed March 27, 2026, 9:18 p.m.
NED1 Entity disambiguation (via context triple) batch_69c845f8b9a48190a21cac7fb98bf26d completed March 28, 2026, 9:19 p.m.
Created at: March 27, 2026, 3:41 p.m.