Triple

T21418348
Position Surface form Disambiguated ID Type / Status
Subject Kobine Festival E528365 entity
Predicate mainLocation P3231 FINISHED
Object Lawra 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: Lawra | Statement: [Kobine Festival, mainLocation, Lawra]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lawra
Context triple: [Kobine Festival, mainLocation, Lawra]
  • A. Lawra chosen
    Lawra is a town in northwestern Ghana that serves as the capital of the Lawra District in the Upper West Region.
  • B. Laja
    Laja is a small Chilean city in the Biobío Region, known for its riverside setting and proximity to the Biobío River.
  • C. Daroach
    Daroach is a recurring mouse-like thief and leader of the Squeaks in the Kirby video game series, known for his cunning schemes and occasional role as an ally.
  • D. Londa
    Londa is a town in the Indian state of Karnataka that serves as an important railway junction and gateway to the Western Ghats.
  • E. Loural
    Loural is a small settlement located within the municipality of Lajes das Flores in the Azores archipelago of Portugal.
  • 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_69e0c454c248819093425d1099101c09 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69ee62d29f948190b820c92014d1c53a completed April 26, 2026, 7:09 p.m.
Created at: April 16, 2026, 5:46 p.m.