Triple

T2807781
Position Surface form Disambiguated ID Type / Status
Subject Bannu E54094 entity
Predicate hasAirport P105 FINISHED
Object Bannu Airport
Bannu Airport is a domestic airport serving the city of Bannu in Khyber Pakhtunkhwa, Pakistan.
E303335 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: Bannu Airport | Statement: [Bannu, hasAirport, Bannu Airport]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bannu Airport
Context triple: [Bannu, hasAirport, Bannu Airport]
  • A. Shah Makhdum Airport
    Shah Makhdum Airport is a regional domestic airport serving the city of Rajshahi in western Bangladesh.
  • B. Dera Ismail Khan Airport
    Dera Ismail Khan Airport is a domestic airport in Khyber Pakhtunkhwa, Pakistan, serving the city of Dera Ismail Khan and its surrounding region.
  • C. Bacha Khan International Airport
    Bacha Khan International Airport is the main international airport serving Peshawar, Pakistan, handling both domestic and international flights for the region.
  • D. Quetta International Airport
    Quetta International Airport is the main domestic and international air gateway serving the city of Quetta and the surrounding region of Balochistan, Pakistan.
  • E. Dalbandin Airport
    Dalbandin Airport is a small domestic airport serving the town of Dalbandin in Balochistan, Pakistan, providing regional air connectivity.
  • 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: Bannu Airport
Triple: [Bannu, hasAirport, Bannu Airport]
Generated description
Bannu Airport is a domestic airport serving the city of Bannu in Khyber Pakhtunkhwa, Pakistan.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Bannu Airport
Target entity description: Bannu Airport is a domestic airport serving the city of Bannu in Khyber Pakhtunkhwa, Pakistan.
  • A. Shah Makhdum Airport
    Shah Makhdum Airport is a regional domestic airport serving the city of Rajshahi in western Bangladesh.
  • B. Dera Ismail Khan Airport
    Dera Ismail Khan Airport is a domestic airport in Khyber Pakhtunkhwa, Pakistan, serving the city of Dera Ismail Khan and its surrounding region.
  • C. Bacha Khan International Airport
    Bacha Khan International Airport is the main international airport serving Peshawar, Pakistan, handling both domestic and international flights for the region.
  • D. Quetta International Airport
    Quetta International Airport is the main domestic and international air gateway serving the city of Quetta and the surrounding region of Balochistan, Pakistan.
  • E. Dalbandin Airport
    Dalbandin Airport is a small domestic airport serving the town of Dalbandin in Balochistan, Pakistan, providing regional air connectivity.
  • 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_69ab49dcee188190b5c6eca9ae9e3469 completed March 6, 2026, 9:40 p.m.
NER Named-entity recognition batch_69abde2fdcf88190a52e515c166ea8f7 completed March 7, 2026, 8:13 a.m.
NED1 Entity disambiguation (via context triple) batch_69afe8aa2bac8190b3c310c7b0e60c75 completed March 10, 2026, 9:47 a.m.
NEDg Description generation batch_69afe8f6a8dc8190b7caae39936fb9e2 completed March 10, 2026, 9:48 a.m.
NED2 Entity disambiguation (via description) batch_69b003b97648819088f279f179286849 completed March 10, 2026, 11:42 a.m.
Created at: March 6, 2026, 9:59 p.m.