Triple

T22214532
Position Surface form Disambiguated ID Type / Status
Subject Ragama E549039 entity
Predicate hasNearbyCity P350 FINISHED
Object Ja-Ela 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: Ja-Ela | Statement: [Ragama, hasNearbyCity, Ja-Ela]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ja-Ela
Context triple: [Ragama, hasNearbyCity, Ja-Ela]
  • A. Ja-Ela chosen
    Ja-Ela is a suburban town in Sri Lanka’s Western Province, situated along the main road between Colombo and Negombo and known as a growing residential and commercial area.
  • B. Ela
    Ela is a feminine given name used in various cultures, often as a short form of names like Eleanor or Elżbieta.
  • C. Jae
    Jae is a professional basketball player best known for his versatile forward play and defensive toughness in the NBA.
  • D. Jega
    Jega is a Nigerian academic and former chairman of the Independent National Electoral Commission, known for overseeing key electoral reforms in Nigeria.
  • E. Junna
    Junna was a 9th-century Japanese emperor of the early Heian period known for his relatively peaceful and stable reign.
  • 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_69e11e3f7e04819089806d81d5ac431e completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f12b8b13f8819099ed8bebbfea3bc8 completed April 28, 2026, 9:50 p.m.
Created at: April 16, 2026, 8:37 p.m.