Triple

T11562741
Position Surface form Disambiguated ID Type / Status
Subject Lower Dir District E274182 entity
Predicate hasSettlement P1068 FINISHED
Object Munda
Munda is a town and administrative settlement located in the Lower Dir District of Khyber Pakhtunkhwa province in Pakistan.
 E933563 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: Munda | Statement: [Lower Dir District, hasSettlement, Munda]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Munda
Context triple: [Lower Dir District, hasSettlement, Munda]
  • A. Munda
    Munda are an indigenous Adivasi community of eastern India known for their distinct Austroasiatic language, rich tribal culture, and historical resistance to colonial rule.
  • B. Munda
    Munda is a town and former World War II airfield site on New Georgia Island in the Western Province of the Solomon Islands.
  • C. Sicel
    Sicel was an ancient Indo-European language once spoken by the Sicel people in eastern Sicily before the dominance of Latin and Greek in the region.
  • D. Casca
    Casca was one of the leading conspirators in the assassination of Julius Caesar, remembered for being among the first to strike during the attack in the Roman Senate.
  • E. Porus
    Porus is a small rural town in Manchester Parish, Jamaica, known historically for its agricultural activities and as a stop along key inland transport routes.
  • 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: Munda
Triple: [Lower Dir District, hasSettlement, Munda]
Generated description
Munda is a town and administrative settlement located in the Lower Dir District of Khyber Pakhtunkhwa province in Pakistan.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Munda
Target entity description: Munda is a town and administrative settlement located in the Lower Dir District of Khyber Pakhtunkhwa province in Pakistan.
  • A. Munda
    Munda are an indigenous Adivasi community of eastern India known for their distinct Austroasiatic language, rich tribal culture, and historical resistance to colonial rule.
  • B. Munda
    Munda is a town and former World War II airfield site on New Georgia Island in the Western Province of the Solomon Islands.
  • C. Sicel
    Sicel was an ancient Indo-European language once spoken by the Sicel people in eastern Sicily before the dominance of Latin and Greek in the region.
  • D. Casca
    Casca was one of the leading conspirators in the assassination of Julius Caesar, remembered for being among the first to strike during the attack in the Roman Senate.
  • E. Porus
    Porus is a small rural town in Manchester Parish, Jamaica, known historically for its agricultural activities and as a stop along key inland transport routes.
  • 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_69d6aae5ac3c81908d2b0a3a665665b2 completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d88dd2016481909b33848af3d1d6c1 completed April 10, 2026, 5:42 a.m.
NED1 Entity disambiguation (via context triple) batch_69e6e89e73b481908175576f4ec8d39a completed April 21, 2026, 3:01 a.m.
NEDg Description generation batch_69e6ef951eb881909810b5923385c4c6 completed April 21, 2026, 3:31 a.m.
NED2 Entity disambiguation (via description) batch_69e6f92ed97c819081576add624dcc27 completed April 21, 2026, 4:12 a.m.
Created at: April 8, 2026, 9:37 p.m.