Triple

T22471211
Position Surface form Disambiguated ID Type / Status
Subject Simbo Island E555505 entity
Predicate hasLocalName P6353 FINISHED
Object Simbo 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: Simbo | Statement: [Simbo Island, hasLocalName, Simbo]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Simbo
Context triple: [Simbo Island, hasLocalName, Simbo]
  • A. Simbo chosen
    Simbo is an Oceanic language of the Meso-Melanesian subgroup spoken on Simbo Island in the Solomon Islands.
  • B. Nyaksimvol
    Nyaksimvol is a small rural locality in the Khanty-Mansi Autonomous Okrug of Russia, situated in the oil-rich region of Western Siberia.
  • C. Tiko
    Tiko is a coastal town and port in southwestern Cameroon known for its agricultural activities and role as a transport hub.
  • D. Simogo
    Simogo is an independent Swedish game development studio known for its stylish, narrative-driven titles that blend music, art, and innovative gameplay.
  • E. Shigmo
    Shigmo is a spring harvest and Holi-related folk festival celebrated with vibrant processions, traditional dances, and music in Goa and the Konkan region of India.
  • 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_69e11e52c2048190952dc5df209b9bed completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15bdf6dfc8190aa8dc80ad92a9267 completed April 29, 2026, 1:16 a.m.
Created at: April 16, 2026, 8:48 p.m.