Triple

T10361293
Position Surface form Disambiguated ID Type / Status
Subject Kurram Agency E244138 entity
Predicate hasTown P847 FINISHED
Object Sadda
Sadda is a town in Pakistan’s Khyber Pakhtunkhwa region, known as a local commercial and administrative center in the Kurram District near the Afghan border.
 E858682 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: Sadda | Statement: [Kurram Agency, hasTown, Sadda]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Sadda
Context triple: [Kurram Agency, hasTown, Sadda]
  • A. Saddar
    Saddar is a major commercial and administrative district in Karachi, Pakistan, known for its bustling markets, colonial-era architecture, and central location.
  • B. Adda
    The Adda is a major river in northern Italy that flows through the Lombardy region and contributes significantly to the water system of the Po basin.
  • C. Bhadar
    Bhadar is a river in the Saurashtra region of Gujarat, India, known for supporting irrigation and local ecosystems along its course.
  • D. Shekhani
    Shekhani is a dialect of the Kati language spoken by communities in parts of Afghanistan and Pakistan.
  • E. Baabda
    Baabda is a town in Lebanon that serves as the administrative center of the Mount Lebanon Governorate and hosts the Lebanese presidential palace.
  • 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: Sadda
Triple: [Kurram Agency, hasTown, Sadda]
Generated description
Sadda is a town in Pakistan’s Khyber Pakhtunkhwa region, known as a local commercial and administrative center in the Kurram District near the Afghan border.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Sadda
Target entity description: Sadda is a town in Pakistan’s Khyber Pakhtunkhwa region, known as a local commercial and administrative center in the Kurram District near the Afghan border.
  • A. Saddar
    Saddar is a major commercial and administrative district in Karachi, Pakistan, known for its bustling markets, colonial-era architecture, and central location.
  • B. Adda
    The Adda is a major river in northern Italy that flows through the Lombardy region and contributes significantly to the water system of the Po basin.
  • C. Bhadar
    Bhadar is a river in the Saurashtra region of Gujarat, India, known for supporting irrigation and local ecosystems along its course.
  • D. Shekhani
    Shekhani is a dialect of the Kati language spoken by communities in parts of Afghanistan and Pakistan.
  • E. Baabda
    Baabda is a town in Lebanon that serves as the administrative center of the Mount Lebanon Governorate and hosts the Lebanese presidential palace.
  • 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_69d381b22b8c8190aaed476be5f872a9 completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4e96209548190957368ee8c6a9ec3 completed April 7, 2026, 11:24 a.m.
NED1 Entity disambiguation (via context triple) batch_69d750bcf00081909b44ffa5df76aec1 completed April 9, 2026, 7:09 a.m.
NEDg Description generation batch_69d7618ecb748190a492406eabe590d7 completed April 9, 2026, 8:21 a.m.
NED2 Entity disambiguation (via description) batch_69d77057affc8190b420e66560c3dfbd completed April 9, 2026, 9:24 a.m.
Created at: April 6, 2026, 11:59 a.m.