Triple

T9248495
Position Surface form Disambiguated ID Type / Status
Subject Upper Guinea E222257 entity
Predicate regionalCapital P3877 FINISHED
Object Kankan E349403 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: Kankan | Statement: [Upper Guinea, regionalCapital, Kankan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kankan
Context triple: [Upper Guinea, regionalCapital, Kankan]
  • A. Kankan (historically) chosen
    Kankan is a historic inland city in eastern Guinea that long served as a major regional trading and cultural center.
  • B. Namba City
    Namba City is a large shopping and entertainment complex in Osaka’s Namba district, featuring retail stores, restaurants, offices, and a rooftop garden integrated with the surrounding urban landscape.
  • C. Kochi
    Kochi is a major port city on the southwest coast of India, known for its historic spice trade, multicultural heritage, and role as a commercial hub in the state of Kerala.
  • D. Kochi
    Kochi is a coastal city on Japan’s Shikoku Island known for its historic castle, vibrant markets, and scenic Pacific shoreline.
  • E. Awaji City
    Awaji City is a municipality located on Awaji Island in Hyōgo Prefecture, Japan, known for its scenic coastal landscapes, agriculture, and cultural heritage.
  • 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_69ca841d2b18819089f9faf5b2c2aec0 completed March 30, 2026, 2:09 p.m.
NER Named-entity recognition batch_69cd05f6d62c8190a1e33f1854767b47 completed April 1, 2026, 11:48 a.m.
NED1 Entity disambiguation (via context triple) batch_69d09bd3fb4c8190a7fa9a60c7f286a0 completed April 4, 2026, 5:04 a.m.
Created at: March 30, 2026, 7:31 p.m.