Triple

T15023803
Position Surface form Disambiguated ID Type / Status
Subject Sukkur Airport E378154 entity
Predicate ICAOCode P419 FINISHED
Object OPSK
OPSK is the ICAO airport code assigned to Sukkur Airport in Pakistan.
E1134274 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: OPSK | Statement: [Sukkur Airport, ICAOCode, OPSK]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: OPSK
Context triple: [Sukkur Airport, ICAOCode, OPSK]
  • A. OPSG
    OPSG is a U.S. federal grant program that provides funding to state, local, and tribal law enforcement agencies to enhance border security and cooperation along international land and water borders.
  • B. OKS
    OKS is the abbreviation commonly used for the National Olympic Committee of Serbia, the body responsible for organizing the country’s participation in the Olympic Games.
  • C. OSO
    OSO is the commonly used abbreviation for the Office of SIGINT Operations, a signals intelligence unit within the U.S. National Security Agency.
  • D. OPST
    OPST is the ICAO airport code for Sialkot International Airport in Sialkot, Pakistan.
  • E. OCS
    OCS (Online Charging System) is a real-time telecommunications billing platform that manages and rates service usage, often working with PCRF to enforce charging and policy decisions.
  • 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: OPSK
Triple: [Sukkur Airport, ICAOCode, OPSK]
Generated description
OPSK is the ICAO airport code assigned to Sukkur Airport in Pakistan.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: OPSK
Target entity description: OPSK is the ICAO airport code assigned to Sukkur Airport in Pakistan.
  • A. OPSG
    OPSG is a U.S. federal grant program that provides funding to state, local, and tribal law enforcement agencies to enhance border security and cooperation along international land and water borders.
  • B. OKS
    OKS is the abbreviation commonly used for the National Olympic Committee of Serbia, the body responsible for organizing the country’s participation in the Olympic Games.
  • C. OSO
    OSO is the commonly used abbreviation for the Office of SIGINT Operations, a signals intelligence unit within the U.S. National Security Agency.
  • D. OPST
    OPST is the ICAO airport code for Sialkot International Airport in Sialkot, Pakistan.
  • E. OCS
    OCS (Original Chip Set) is the first-generation custom graphics and sound chipset used in early Commodore Amiga computers, providing advanced multimedia capabilities for its time.
  • 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_69d85cd46b2c819090d054c27787f677 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69ded7de117c8190a1b9fa8d1602057e completed April 15, 2026, 12:12 a.m.
NED1 Entity disambiguation (via context triple) batch_69fe9dd499108190b803c6afc0fa00bc completed May 9, 2026, 2:37 a.m.
NEDg Description generation batch_69fea09ea0e081908daed335c734c8c0 completed May 9, 2026, 2:49 a.m.
NED2 Entity disambiguation (via description) batch_69fea0fd72508190a413f5bb07d1df28 completed May 9, 2026, 2:50 a.m.
Created at: April 10, 2026, 2:56 a.m.