Triple

T7472187
Position Surface form Disambiguated ID Type / Status
Subject Halim Perdanakusuma International Airport E176533 entity
Predicate ICAOcode P419 FINISHED
Object WIHH
WIHH is the ICAO airport code for Halim Perdanakusuma International Airport serving Jakarta, Indonesia.
 E667373 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: WIHH | Statement: [Halim Perdanakusuma International Airport, ICAOcode, WIHH]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: WIHH
Context triple: [Halim Perdanakusuma International Airport, ICAOcode, WIHH]
  • A. HWI
    HWI is the National Rail station code for Horwich Parkway railway station in Greater Manchester, England.
  • B. HWI
    HWI is the vehicle registration code for the German town of Wismar in the state of Mecklenburg-Vorpommern.
  • C. WICC
    WICC is the ICAO airport code for Husein Sastranegara International Airport in Bandung, Indonesia.
  • D. IHA
    IHA is the commonly used abbreviation for Japan’s Imperial Household Agency, the government body responsible for matters concerning the Imperial Family.
  • E. HIH
    HIH is an honorific abbreviation used to refer to a female member of an imperial family bearing the style "Her Imperial Highness."
  • 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: WIHH
Triple: [Halim Perdanakusuma International Airport, ICAOcode, WIHH]
Generated description
WIHH is the ICAO airport code for Halim Perdanakusuma International Airport serving Jakarta, Indonesia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: WIHH
Target entity description: WIHH is the ICAO airport code for Halim Perdanakusuma International Airport serving Jakarta, Indonesia.
  • A. HWI
    HWI is the National Rail station code for Horwich Parkway railway station in Greater Manchester, England.
  • B. HWI
    HWI is the vehicle registration code for the German town of Wismar in the state of Mecklenburg-Vorpommern.
  • C. WICC
    WICC is the ICAO airport code for Husein Sastranegara International Airport in Bandung, Indonesia.
  • D. IHA
    IHA is the commonly used abbreviation for Japan’s Imperial Household Agency, the government body responsible for matters concerning the Imperial Family.
  • E. HIH
    HIH is an honorific abbreviation used to refer to a female member of an imperial family bearing the style "Her Imperial Highness."
  • 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_69c69f223fd88190b4c69b95d7cbeeda completed March 27, 2026, 3:15 p.m.
NER Named-entity recognition batch_69c6f415b5cc81909e1e097c90f460b6 completed March 27, 2026, 9:18 p.m.
NED1 Entity disambiguation (via context triple) batch_69c83480a40c8190a7ae3e08022735a1 completed March 28, 2026, 8:05 p.m.
NEDg Description generation batch_69c835ce5bbc8190b968535c16cfc660 completed March 28, 2026, 8:10 p.m.
NED2 Entity disambiguation (via description) batch_69c836a80eb081908b9937944fe18661 completed March 28, 2026, 8:14 p.m.
Created at: March 27, 2026, 3:41 p.m.