Triple

T20904635
Position Surface form Disambiguated ID Type / Status
Subject Manikganj District E514760 entity
Predicate hasSettlement P1068 FINISHED
Object Manikganj town 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: Manikganj town | Statement: [Manikganj District, hasSettlement, Manikganj town]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Manikganj town
Context triple: [Manikganj District, hasSettlement, Manikganj town]
  • A. Manikganj chosen
    Manikganj is a town in central Bangladesh that serves as the administrative and commercial hub of Manikganj District.
  • B. Begumganj
    Begumganj is a town and administrative subdivision in the Raisen district of Madhya Pradesh, India.
  • C. Jamalpur
    Jamalpur is a city in central Bangladesh known as an important regional hub for agriculture and trade near the Jamuna River.
  • D. Liaquatabad Town
    Liaquatabad Town is a densely populated residential and commercial locality in Karachi, Pakistan, known for its bustling markets and central urban location.
  • E. Keraniganj
    Keraniganj is a suburban upazila of Dhaka, Bangladesh, known for its dense population, river-based commerce, and numerous garment and brick industries.
  • 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_69e0b4f8a1108190bce3d31331290ced completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6e8ff36488190987ecdfcbed4220c completed April 21, 2026, 3:03 a.m.
Created at: April 16, 2026, 12:47 p.m.