Triple

T21431068
Position Surface form Disambiguated ID Type / Status
Subject Sumba E528683 entity
Predicate hasNearbySettlement P4647 FINISHED
Object Lopra NE NERFINISHED

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: Lopra | Statement: [Sumba, hasNearbySettlement, Lopra]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lopra
Context triple: [Sumba, hasNearbySettlement, Lopra]
  • A. Lopra chosen
    Lopra is a small village located on the island of Suðuroy in the Faroe Islands.
  • B. Lopar
    Lopar is a coastal village and popular tourist resort located on the northern part of the Croatian island of Rab, known for its sandy beaches such as Paradise Beach.
  • C. Lopat
    Lopat is a place name derived from the original form "Lopatynski," likely referring to a locality or surname variant in a Slavic-speaking region.
  • D. Lopevi
    Lopevi is an Oceanic language of Vanuatu, traditionally spoken on Lopevi Island in the central part of the archipelago.
  • E. Arpora
    Arpora is a village in the Indian state of Goa, known for its popular Saturday Night Market and proximity to major beach destinations like Baga and Calangute.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e0c455f3688190810bc96365791b0f completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69e8b3eb08988190b50eca911442de7c completed April 22, 2026, 11:41 a.m.
Created at: April 16, 2026, 5:49 p.m.