Triple

T12696065
Position Surface form Disambiguated ID Type / Status
Subject Bannu Basin E303336 entity
Predicate hasArchaeologicalSite P1098 FINISHED
Object Lewan
Lewan is an archaeological site in Pakistan’s Bannu Basin known for evidence of ancient human settlement and cultural development.
 E998300 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: Lewan | Statement: [Bannu Basin, hasArchaeologicalSite, Lewan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Lewan
Context triple: [Bannu Basin, hasArchaeologicalSite, Lewan]
  • A. Lahndi
    Lahndi is an Indo-Aryan language (or group of dialects) spoken primarily in western parts of Pakistan, often considered a dialect continuum between Punjabi and Sindhi.
  • B. Leme
    Leme is a beachfront neighborhood in Rio de Janeiro known for its quieter stretch of sand adjoining Copacabana and its scenic views of the Atlantic and surrounding hills.
  • C. Tazzelenghe
    Tazzelenghe is a rare, intensely tannic red wine grape native to Italy’s Friuli region, known for producing deeply colored, robust wines with pronounced acidity and dark fruit flavors.
  • D. Maleka
    Maleka is a feminine given name, typically considered a variant spelling of Malika and used in various cultures.
  • E. Wanze
    Wanze is a municipality in eastern Belgium situated along the Meuse River in the Walloon Region.
  • 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: Lewan
Triple: [Bannu Basin, hasArchaeologicalSite, Lewan]
Generated description
Lewan is an archaeological site in Pakistan’s Bannu Basin known for evidence of ancient human settlement and cultural development.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Lewan
Target entity description: Lewan is an archaeological site in Pakistan’s Bannu Basin known for evidence of ancient human settlement and cultural development.
  • A. Lahndi
    Lahndi is an Indo-Aryan language (or group of dialects) spoken primarily in western parts of Pakistan, often considered a dialect continuum between Punjabi and Sindhi.
  • B. Leme
    Leme is a beachfront neighborhood in Rio de Janeiro known for its quieter stretch of sand adjoining Copacabana and its scenic views of the Atlantic and surrounding hills.
  • C. Tazzelenghe
    Tazzelenghe is a rare, intensely tannic red wine grape native to Italy’s Friuli region, known for producing deeply colored, robust wines with pronounced acidity and dark fruit flavors.
  • D. Maleka
    Maleka is a feminine given name, typically considered a variant spelling of Malika and used in various cultures.
  • E. Wanze
    Wanze is a municipality in eastern Belgium situated along the Meuse River in the Walloon Region.
  • 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_69d7bdef90d48190b46b88270e780946 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d961ebd17081909f983567e4b36533 completed April 10, 2026, 8:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69f671ae935c8190a7fc2cf3c0987248 completed May 2, 2026, 9:50 p.m.
NEDg Description generation batch_69f6740129688190b286ce7acb4848c7 completed May 2, 2026, 10 p.m.
NED2 Entity disambiguation (via description) batch_69f675249d248190933421df49d3a2ab completed May 2, 2026, 10:05 p.m.
Created at: April 9, 2026, 5:22 p.m.