Triple

T20046963
Position Surface form Disambiguated ID Type / Status
Subject H.A.S. Hanandjoeddin International Airport E497584 entity
Predicate IATA code P2569 FINISHED
Object TJQ
TJQ is the IATA airport code for H.A.S. Hanandjoeddin International Airport serving Belitung Island in Indonesia.
E1409229 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: TJQ | Statement: [H.A.S. Hanandjoeddin International Airport, IATA code, TJQ]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: TJQ
Context triple: [H.A.S. Hanandjoeddin International Airport, IATA code, TJQ]
  • A. TJBQ
    TJBQ is the ICAO airport code for Rafael Hernández Airport, a public international airport serving Aguadilla in Puerto Rico.
  • B. TJ
    TJ is a highly selective, STEM-focused public magnet high school in Northern Virginia renowned for its rigorous academics and advanced research opportunities.
  • C. TJ
    TJ is the two-letter ISO 3166-1 alpha-2 country code assigned to Tajikistan.
  • D. TJ
    TJ is the commonly used abbreviation for TransJakarta, Jakarta’s bus rapid transit system.
  • E. TJ
    TJ is a software developer best known for creating the Node.js web framework Express and numerous other open-source tools.
  • 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: TJQ
Triple: [H.A.S. Hanandjoeddin International Airport, IATA code, TJQ]
Generated description
TJQ is the IATA airport code for H.A.S. Hanandjoeddin International Airport serving Belitung Island in Indonesia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: TJQ
Target entity description: TJQ is the IATA airport code for H.A.S. Hanandjoeddin International Airport serving Belitung Island in Indonesia.
  • A. TJBQ
    TJBQ is the ICAO airport code for Rafael Hernández Airport, a public international airport serving Aguadilla in Puerto Rico.
  • B. TJ
    TJ is the commonly used abbreviation for TransJakarta, Jakarta’s bus rapid transit system.
  • C. TJ
    TJ is the two-letter ISO 3166-1 alpha-2 country code assigned to Tajikistan.
  • D. TJ
    TJ is a highly selective, STEM-focused public magnet high school in Northern Virginia renowned for its rigorous academics and advanced research opportunities.
  • E. TJ
    TJ is a software developer best known for creating the Node.js web framework Express and numerous other open-source tools.
  • 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_69da627278c88190babe4297a9df1236 completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e6632b2de48190abe2b277d89eb695 completed April 20, 2026, 5:32 p.m.
NED1 Entity disambiguation (via context triple) batch_6a081603b36c8190b82688c3235fc794 completed May 16, 2026, 7 a.m.
NEDg Description generation batch_6a08180e5e988190a846aef83802cfc3 completed May 16, 2026, 7:09 a.m.
NED2 Entity disambiguation (via description) batch_6a0818970bb081908093589df4fc65b6 completed May 16, 2026, 7:11 a.m.
Created at: April 11, 2026, 3:37 p.m.