Triple

T9667784
Position Surface form Disambiguated ID Type / Status
Subject Haikou Meilan International Airport E233748 entity
Predicate IATAcode P418 FINISHED
Object HAK
HAK is the IATA airport code for Haikou Meilan International Airport, the main air gateway to Haikou in China’s Hainan Province.
 E813024 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: HAK | Statement: [Haikou Meilan International Airport, IATAcode, HAK]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: HAK
Context triple: [Haikou Meilan International Airport, IATAcode, HAK]
  • A. Haki
    Haki is the given name of Haki R. Madhubuti, a prominent African-American poet, publisher, and leading figure of the Black Arts Movement.
  • B. Haql
    Haql is a small coastal town in northwestern Saudi Arabia on the Red Sea's Gulf of Aqaba, known for its clear waters, coral reefs, and views of neighboring Egypt and Jordan.
  • C. haka
    The haka is a traditional Māori ceremonial dance or challenge from New Zealand, characterized by vigorous movements and chanting, often performed to display pride, strength, and unity.
  • D. Haqniq
    Haqniq is the self-designated name (autonym) used by speakers of the Hani language for themselves or their language.
  • E. Haq
    Haq is a common surname of Arabic origin used across South Asia and the Muslim world, often associated with scholars, public figures, and professionals.
  • 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: HAK
Triple: [Haikou Meilan International Airport, IATAcode, HAK]
Generated description
HAK is the IATA airport code for Haikou Meilan International Airport, the main air gateway to Haikou in China’s Hainan Province.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: HAK
Target entity description: HAK is the IATA airport code for Haikou Meilan International Airport, the main air gateway to Haikou in China’s Hainan Province.
  • A. Haki
    Haki is the given name of Haki R. Madhubuti, a prominent African-American poet, publisher, and leading figure of the Black Arts Movement.
  • B. Haql
    Haql is a small coastal town in northwestern Saudi Arabia on the Red Sea's Gulf of Aqaba, known for its clear waters, coral reefs, and views of neighboring Egypt and Jordan.
  • C. haka
    The haka is a traditional Māori ceremonial dance or challenge from New Zealand, characterized by vigorous movements and chanting, often performed to display pride, strength, and unity.
  • D. Haqniq
    Haqniq is the self-designated name (autonym) used by speakers of the Hani language for themselves or their language.
  • E. Haq
    Haq is a common surname of Arabic origin used across South Asia and the Muslim world, often associated with scholars, public figures, and professionals.
  • 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_69ca848d3b6c8190ae98ea554dea58df completed March 30, 2026, 2:11 p.m.
NER Named-entity recognition batch_69cd9c3c06e4819080c1b8e66faa482f completed April 1, 2026, 10:29 p.m.
NED1 Entity disambiguation (via context triple) batch_69d18a208798819088db055e44d288e3 completed April 4, 2026, 10:01 p.m.
NEDg Description generation batch_69d18ab1239c8190b4a66ccd0db35ffb completed April 4, 2026, 10:03 p.m.
NED2 Entity disambiguation (via description) batch_69d18b7f7510819083a402d6802c7d95 completed April 4, 2026, 10:06 p.m.
Created at: March 30, 2026, 8:15 p.m.