Triple

T7362427
Position Surface form Disambiguated ID Type / Status
Subject Maumere E169782 entity
Predicate servedBy P82 FINISHED
Object Frans Seda Airport E661400 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: Frans Seda Airport | Statement: [Maumere, servedBy, Frans Seda Airport]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Frans Seda Airport
Context triple: [Maumere, servedBy, Frans Seda Airport]
  • A. Frans Seda Airport chosen
    Frans Seda Airport is a regional airport serving the town of Maumere on the island of Flores in Indonesia.
  • B. Hewanorra International Airport
    Hewanorra International Airport is the main international gateway to Saint Lucia, serving as the island’s primary hub for long-haul and regional flights.
  • C. Hang Nadim International Airport
    Hang Nadim International Airport is the main commercial airport serving Batam, Indonesia, known for its long runway and role as a regional aviation hub in the Riau Islands.
  • D. Ulei Airport
    Ulei Airport is a small regional airfield serving the island of Ambrym in Vanuatu, providing local and inter-island air connections.
  • E. Uytash Airport
    Uytash Airport is the main civil airport serving the city of Makhachkala and the Republic of Dagestan in southern Russia.
  • 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_69c68a5ade988190885b7175f63b7534 completed March 27, 2026, 1:47 p.m.
NER Named-entity recognition batch_69c6f15f218081909b5cc7a8cc695055 completed March 27, 2026, 9:06 p.m.
NED1 Entity disambiguation (via context triple) batch_69c81ec20db88190b68542feaa9d66ef completed March 28, 2026, 6:32 p.m.
Created at: March 27, 2026, 3:06 p.m.