Triple

T10540638
Position Surface form Disambiguated ID Type / Status
Subject Paktika Province E248683 entity
Predicate hasNotableTown P14082 FINISHED
Object Yahya Khel
Yahya Khel is a town in southeastern Afghanistan located within Paktika Province.
 E870994 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: Yahya Khel | Statement: [Paktika Province, hasNotableTown, Yahya Khel]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Yahya Khel
Context triple: [Paktika Province, hasNotableTown, Yahya Khel]
  • A. Musa Khel
    Musa Khel is a Pashtun tribe belonging to the Karlani confederation, primarily found in regions of Afghanistan and Pakistan.
  • B. Hassan Ali
    Hassan Ali is a given name commonly used in Muslim communities, notably borne by figures such as the 19th-century educationist Hassan Ali Effendi of British India.
  • C. Hasnat Khan
    Hasnat Khan is a British-Pakistani heart surgeon best known for his romantic relationship with Diana, Princess of Wales.
  • D. Bilall Fallah
    Bilall Fallah is a Belgian film director known for his energetic, action-driven style and for co-directing major Hollywood projects such as "Bad Boys for Life."
  • E. Zahir Raheem
    Zahir Raheem is an American former professional boxer best known as a skilled featherweight and lightweight contender who scored notable upsets over several high-profile opponents.
  • 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: Yahya Khel
Triple: [Paktika Province, hasNotableTown, Yahya Khel]
Generated description
Yahya Khel is a town in southeastern Afghanistan located within Paktika Province.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Yahya Khel
Target entity description: Yahya Khel is a town in southeastern Afghanistan located within Paktika Province.
  • A. Musa Khel
    Musa Khel is a Pashtun tribe belonging to the Karlani confederation, primarily found in regions of Afghanistan and Pakistan.
  • B. Hassan Ali
    Hassan Ali is a given name commonly used in Muslim communities, notably borne by figures such as the 19th-century educationist Hassan Ali Effendi of British India.
  • C. Hasnat Khan
    Hasnat Khan is a British-Pakistani heart surgeon best known for his romantic relationship with Diana, Princess of Wales.
  • D. Bilall Fallah
    Bilall Fallah is a Belgian film director known for his energetic, action-driven style and for co-directing major Hollywood projects such as "Bad Boys for Life."
  • E. Zahir Raheem
    Zahir Raheem is an American former professional boxer best known as a skilled featherweight and lightweight contender who scored notable upsets over several high-profile opponents.
  • 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_69d381c733c08190ab1dd6239f5f34ae completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d50a582be48190856c6f272eea4dcf completed April 7, 2026, 1:44 p.m.
NED1 Entity disambiguation (via context triple) batch_69d9341d96c08190a6ba644b9acfe2c8 completed April 10, 2026, 5:32 p.m.
NEDg Description generation batch_69d93802a4488190aa86ae209650d4e7 completed April 10, 2026, 5:48 p.m.
NED2 Entity disambiguation (via description) batch_69d938fcc3c48190a4acaaf75c1aa304 completed April 10, 2026, 5:53 p.m.
Created at: April 6, 2026, 12:32 p.m.