Triple

T15058392
Position Surface form Disambiguated ID Type / Status
Subject Gampaha District E379556 entity
Predicate contains P35 FINISHED
Object Mahara
Mahara is a suburban town in Sri Lanka’s Western Province, situated within the Gampaha District and known for its residential communities and local institutions.
E1135858 NE FINISHED

How this triple was built (4 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: Mahara | Statement: [Gampaha District, contains, Mahara]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mahara
Context triple: [Gampaha District, contains, Mahara]
  • A. Sakai
    Sakai is a major Japanese city in Osaka Prefecture known historically as a prosperous port and merchant center and today as an important industrial and cultural hub.
  • B. Mabang
    Mabang is an alternative name for the Maba language, a Nilo-Saharan language spoken primarily in Chad.
  • C. Alura
    Alura is Supergirl’s Kryptonian mother, often depicted as a prominent scientist and leader on Krypton in DC Comics lore.
  • D. Sakai Port
    Sakai Port is a historic Japanese harbor city area in Osaka Prefecture that has long served as a key commercial and maritime gateway.
  • E. Tantripala
    Tantripala is an alternate name for Sahadeva, one of the five Pandava princes in the Indian epic Mahabharata.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Mahara
Triple: [Gampaha District, contains, Mahara]
Generated description
Mahara is a suburban town in Sri Lanka’s Western Province, situated within the Gampaha District and known for its residential communities and local institutions.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Mahara
Target entity description: Mahara is a suburban town in Sri Lanka’s Western Province, situated within the Gampaha District and known for its residential communities and local institutions.
  • A. Sakai
    Sakai is a major Japanese city in Osaka Prefecture known historically as a prosperous port and merchant center and today as an important industrial and cultural hub.
  • B. Mabang
    Mabang is an alternative name for the Maba language, a Nilo-Saharan language spoken primarily in Chad.
  • C. Alura
    Alura is Supergirl’s Kryptonian mother, often depicted as a prominent scientist and leader on Krypton in DC Comics lore.
  • D. Sakai Port
    Sakai Port is a historic Japanese harbor city area in Osaka Prefecture that has long served as a key commercial and maritime gateway.
  • E. Tantripala
    Tantripala is an alternate name for Sahadeva, one of the five Pandava princes in the Indian epic Mahabharata.
  • F. None of above. chosen

Provenance (5 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_69d85cd64d108190853797a95c11cc45 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69dedee50afc8190bf7b0f4bbe8c60a3 completed April 15, 2026, 12:42 a.m.
NED1 Entity disambiguation (via context triple) batch_69fea5c2fcec8190800d1bda82c7352e completed May 9, 2026, 3:10 a.m.
NEDg Description generation batch_69fea9c0ad748190989920efe418001c completed May 9, 2026, 3:28 a.m.
NED2 Entity disambiguation (via description) batch_69feaa2fbafc8190b592d89b07b49765 completed May 9, 2026, 3:29 a.m.
Created at: April 10, 2026, 3:01 a.m.