Triple

T14279185
Position Surface form Disambiguated ID Type / Status
Subject Hiva Oa Airport E353996 entity
Predicate IATACode P418 FINISHED
Object AUQ
AUQ is the IATA airport code for Hiva Oa Airport in the Marquesas Islands of French Polynesia.
E1088998 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: AUQ | Statement: [Hiva Oa Airport, IATACode, AUQ]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: AUQ
Context triple: [Hiva Oa Airport, IATACode, AUQ]
  • A. AQ
    AQ is an Oracle Database feature that provides message-based communication and queuing capabilities for building asynchronous, distributed applications.
  • B. AQJ
    AQJ is the IATA airport code for King Hussein International Airport serving Aqaba, Jordan.
  • C. UAQ
    UAQ is the vehicle registration code used on license plates issued in the emirate of Umm Al Quwain in the United Arab Emirates.
  • D. AQN
    AQN is the station code for Lisbon Metro’s Antero de Quental station on the city’s urban rail network.
  • E. ANQ
    ANQ is the commonly used acronym for the National Assembly of Quebec, the unicameral legislative body of the Canadian province of Quebec.
  • 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: AUQ
Triple: [Hiva Oa Airport, IATACode, AUQ]
Generated description
AUQ is the IATA airport code for Hiva Oa Airport in the Marquesas Islands of French Polynesia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: AUQ
Target entity description: AUQ is the IATA airport code for Hiva Oa Airport in the Marquesas Islands of French Polynesia.
  • A. AQ
    AQ is an Oracle Database feature that provides message-based communication and queuing capabilities for building asynchronous, distributed applications.
  • B. AQJ
    AQJ is the IATA airport code for King Hussein International Airport serving Aqaba, Jordan.
  • C. UAQ
    UAQ is the vehicle registration code used on license plates issued in the emirate of Umm Al Quwain in the United Arab Emirates.
  • D. AQN
    AQN is the station code for Lisbon Metro’s Antero de Quental station on the city’s urban rail network.
  • E. ANQ
    ANQ is the commonly used acronym for the National Assembly of Quebec, the unicameral legislative body of the Canadian province of Quebec.
  • 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_69d8278d25148190abf1a8c8f5f533ad completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de6585270c8190a717127b2f5dab3b completed April 14, 2026, 4:04 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd32719ecc8190b57aad5197521359 completed May 8, 2026, 12:46 a.m.
NEDg Description generation batch_69fd333b49a88190834a5f45fa0fc6c2 completed May 8, 2026, 12:50 a.m.
NED2 Entity disambiguation (via description) batch_69fd33bdc8d08190be11f5ccf259cd6a completed May 8, 2026, 12:52 a.m.
Created at: April 10, 2026, 1:10 a.m.