Triple

T14643994
Position Surface form Disambiguated ID Type / Status
Subject Hualien Air Base E343796 entity
Predicate hasIATAcode P2569 FINISHED
Object HUN
HUN is the IATA airport code for Hualien Airport, a civil-military airport serving Hualien in eastern Taiwan.
 E1111496 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: HUN | Statement: [Hualien Air Base, hasIATAcode, HUN]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: HUN
Context triple: [Hualien Air Base, hasIATAcode, HUN]
  • A. HUN
    HUN is the three-letter International Olympic Committee country code used to represent Hungary in Olympic competitions and related events.
  • B. HUN
    HUN is the three-letter National Rail station code for Huntingdon railway station in Cambridgeshire, England.
  • C. Huny
    Huny is an alternative transliteration of Huni, an ancient Egyptian pharaoh of the Third Dynasty.
  • D. Hun
    The Huns were a nomadic confederation of Central Asian horsemen who became infamous in late antiquity for their fierce military campaigns and invasions of Europe.
  • E. Hóngrěn
    Hóngrěn is a romanized Chinese name, written in Hanyu Pinyin, that can refer to various individuals depending on the context.
  • 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: HUN
Triple: [Hualien Air Base, hasIATAcode, HUN]
Generated description
HUN is the IATA airport code for Hualien Airport, a civil-military airport serving Hualien in eastern Taiwan.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: HUN
Target entity description: HUN is the IATA airport code for Hualien Airport, a civil-military airport serving Hualien in eastern Taiwan.
  • A. HUN
    HUN is the three-letter International Olympic Committee country code used to represent Hungary in Olympic competitions and related events.
  • B. HUN
    HUN is the three-letter National Rail station code for Huntingdon railway station in Cambridgeshire, England.
  • C. Huny
    Huny is an alternative transliteration of Huni, an ancient Egyptian pharaoh of the Third Dynasty.
  • D. Hun
    The Huns were a nomadic confederation of Central Asian horsemen who became infamous in late antiquity for their fierce military campaigns and invasions of Europe.
  • E. Hóngrěn
    Hóngrěn is a romanized Chinese name, written in Hanyu Pinyin, that can refer to various individuals depending on the context.
  • 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_69d822e1a2cc81908e5bb93cf61ce3cc completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69deb4ea6d8481908e6331ca173c646b completed April 14, 2026, 9:43 p.m.
NED1 Entity disambiguation (via context triple) batch_69fdd5d5d05481908dbb23392c05d23b completed May 8, 2026, 12:23 p.m.
NEDg Description generation batch_69fdd74cc4048190bae5f75d922c9618 completed May 8, 2026, 12:30 p.m.
NED2 Entity disambiguation (via description) batch_69fdd7bd20748190b9145ef14ce2759b completed May 8, 2026, 12:31 p.m.
Created at: April 10, 2026, 1:26 a.m.