Triple

T14886907
Position Surface form Disambiguated ID Type / Status
Subject Larkana District E350149 entity
Predicate contains P35 FINISHED
Object Larkana city
Larkana city is a major urban center in Sindh, Pakistan, known as the hometown of the Bhutto political family and for its proximity to the ancient Indus Valley site of Mohenjo-daro.
E1126122 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: Larkana city | Statement: [Larkana District, contains, Larkana city]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Larkana city
Context triple: [Larkana District, contains, Larkana city]
  • A. Haroonabad
    Haroonabad is a town in Pakistan known for its agricultural surroundings and role as a local commercial center.
  • B. Jauharabad
    Jauharabad is a planned town in Pakistan’s Punjab province, known for its proximity to key industrial and strategic facilities.
  • C. Shahabad
    Shahabad is a town in Uttar Pradesh, India, situated within the administrative boundaries of Rampur district.
  • D. Wazirabad
    Wazirabad is a city in the Gujranwala District of Punjab, Pakistan, known for its cutlery industry and strategic location near the Chenab River.
  • E. Bhurban
    Bhurban is a small, scenic hill resort in Pakistan’s Punjab province, known for its lush forests, cool climate, and popular hotels and golf course.
  • 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: Larkana city
Triple: [Larkana District, contains, Larkana city]
Generated description
Larkana city is a major urban center in Sindh, Pakistan, known as the hometown of the Bhutto political family and for its proximity to the ancient Indus Valley site of Mohenjo-daro.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Larkana city
Target entity description: Larkana city is a major urban center in Sindh, Pakistan, known as the hometown of the Bhutto political family and for its proximity to the ancient Indus Valley site of Mohenjo-daro.
  • A. Haroonabad
    Haroonabad is a town in Pakistan known for its agricultural surroundings and role as a local commercial center.
  • B. Jauharabad
    Jauharabad is a planned town in Pakistan’s Punjab province, known for its proximity to key industrial and strategic facilities.
  • C. Shahabad
    Shahabad is a town in Uttar Pradesh, India, situated within the administrative boundaries of Rampur district.
  • D. Wazirabad
    Wazirabad is a city in the Gujranwala District of Punjab, Pakistan, known for its cutlery industry and strategic location near the Chenab River.
  • E. Bhurban
    Bhurban is a small, scenic hill resort in Pakistan’s Punjab province, known for its lush forests, cool climate, and popular hotels and golf course.
  • 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_69d822ee4f408190b6ac3b2fa434f0df completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69ded5f5b1c88190815f3585770cb135 completed April 15, 2026, 12:04 a.m.
NED1 Entity disambiguation (via context triple) batch_69fe6b5f22c08190a9530cbd78cfc801 completed May 8, 2026, 11:01 p.m.
NEDg Description generation batch_69fe6f9b33748190aee0c27879866ca1 completed May 8, 2026, 11:19 p.m.
NED2 Entity disambiguation (via description) batch_69fe703e8c28819081b7bfe638a2202e completed May 8, 2026, 11:22 p.m.
Created at: April 10, 2026, 1:56 a.m.