Triple

T9930176
Position Surface form Disambiguated ID Type / Status
Subject Tokunoshima Airport E192626 entity
Predicate serves P98 FINISHED
Object Isen E198618 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: Isen | Statement: [Tokunoshima Airport, serves, Isen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Isen
Context triple: [Tokunoshima Airport, serves, Isen]
  • A. Isen chosen
    Isen is a small town located on Tokunoshima in Japan’s Amami Islands, known for its subtropical climate and coastal scenery.
  • B. Teisen
    Teisen is a residential neighborhood in Oslo, Norway, known for its apartment blocks, green spaces, and convenient access to public transportation.
  • C. Uineasan
    Uineasan is a small, lesser-known island that forms part of the Barra Isles archipelago in Scotland’s Outer Hebrides.
  • D. Ennesi
    Ennesi are the inhabitants or natives of the city of Enna in central Sicily, Italy.
  • E. Rairi
    Rairi is the historical name of Raigad Fort, a prominent hill fort in Maharashtra, India, closely associated with the Maratha ruler Chhatrapati Shivaji Maharaj.
  • 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_69ca82dd978c8190947124ab0d3315ac completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cdb5b4196881909a004091a4203c45 completed April 2, 2026, 12:17 a.m.
NED1 Entity disambiguation (via context triple) batch_69d228cab0fc81908ff5fad6916c1bab completed April 5, 2026, 9:18 a.m.
Created at: March 30, 2026, 8:43 p.m.