Triple

T7018160
Position Surface form Disambiguated ID Type / Status
Subject AGX E162747 entity
Predicate appliesTo P1129 FINISHED
Object Agatti Airport E31978 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: Agatti Airport | Statement: [AGX, appliesTo, Agatti Airport]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Agatti Airport
Context triple: [AGX, appliesTo, Agatti Airport]
  • A. Agatti Airport chosen
    Agatti Airport is a small domestic airport in Lakshadweep, India, serving as the primary air link to the Agatti Island and the surrounding archipelago in the Arabian Sea.
  • B. Palali Airport
    Palali Airport is a regional airport in northern Sri Lanka that serves the Jaffna Peninsula and has been developed for both civilian and military use.
  • C. Punta Raisi Airport
    Punta Raisi Airport is the main international airport serving Palermo and the surrounding region in Sicily, Italy.
  • D. Socotra Airport
    Socotra Airport is the main air gateway to Yemen’s remote Socotra Island, connecting the UNESCO-recognized archipelago with the mainland and limited international destinations.
  • E. Calicut International Airport
    Calicut International Airport is a major international airport in the Malabar region of Kerala, India, serving the city of Kozhikode and surrounding areas with extensive domestic and Gulf-region connectivity.
  • 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_69c6885a127c8190867b059bdccf13ff completed March 27, 2026, 1:38 p.m.
NER Named-entity recognition batch_69c6e1e79c108190a507335e9dbf2716 completed March 27, 2026, 8 p.m.
NED1 Entity disambiguation (via context triple) batch_69c7884ac340819093e1812738d5e30f completed March 28, 2026, 7:50 a.m.
Created at: March 27, 2026, 2:34 p.m.