Triple

T1640706
Position Surface form Disambiguated ID Type / Status
Subject Haneda Airport E35463 entity
Predicate IATAcode P418 FINISHED
Object HND
HND is the IATA airport code for Tokyo International Airport, commonly known as Haneda Airport, one of Japan’s busiest and primary airports serving the Tokyo metropolitan area.
 E186914 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: HND | Statement: [Haneda Airport, IATAcode, HND]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: HND
Context triple: [Haneda Airport, IATAcode, HND]
  • A. HND
    HND is the three-letter ISO 3166-1 alpha-3 country code assigned to Honduras.
  • B. DGPA
    DGPA is the abbreviated name of France’s Direction générale des patrimoines et de l’architecture, the national authority responsible for heritage and architectural policy.
  • C. HN
    HN is the two-letter ISO 3166-1 alpha-2 country code assigned to Honduras.
  • D. DNP
    DNP is the commonly used abbreviation for the Division of Nuclear Physics, a professional organization focused on research and advancement in nuclear physics.
  • E. DSE
    DSE is a premier postgraduate institution of the University of Delhi renowned for its programs and research in economics and related social sciences.
  • 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: HND
Triple: [Haneda Airport, IATAcode, HND]
Generated description
HND is the IATA airport code for Tokyo International Airport, commonly known as Haneda Airport, one of Japan’s busiest and primary airports serving the Tokyo metropolitan area.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: HND
Target entity description: HND is the IATA airport code for Tokyo International Airport, commonly known as Haneda Airport, one of Japan’s busiest and primary airports serving the Tokyo metropolitan area.
  • A. HND
    HND is the three-letter ISO 3166-1 alpha-3 country code assigned to Honduras.
  • B. DGPA
    DGPA is the abbreviated name of France’s Direction générale des patrimoines et de l’architecture, the national authority responsible for heritage and architectural policy.
  • C. HN
    HN is the two-letter ISO 3166-1 alpha-2 country code assigned to Honduras.
  • D. DNP
    DNP is the commonly used abbreviation for the Division of Nuclear Physics, a professional organization focused on research and advancement in nuclear physics.
  • E. DSE
    DSE is a premier postgraduate institution of the University of Delhi renowned for its programs and research in economics and related social sciences.
  • 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_69a88604618c81908b41f6429c431eb6 completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69a90a3c883c8190bec1d87ecedf2575 completed March 5, 2026, 4:44 a.m.
NED1 Entity disambiguation (via context triple) batch_69ad609cf8488190ba334bdff2c5e78d completed March 8, 2026, 11:42 a.m.
NEDg Description generation batch_69ad61ff65b881909009c230780a146e completed March 8, 2026, 11:48 a.m.
NED2 Entity disambiguation (via description) batch_69ad62ec3a80819085fef1c378b9abdc completed March 8, 2026, 11:52 a.m.
Created at: March 4, 2026, 7:28 p.m.