Triple

T5750562
Position Surface form Disambiguated ID Type / Status
Subject Tweed New Haven Airport E126841 entity
Predicate IATACode P418 FINISHED
Object HVN
HVN is the IATA airport code for Tweed New Haven Airport, a regional airport serving New Haven, Connecticut.
 E543602 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: HVN | Statement: [Tweed New Haven Airport, IATACode, HVN]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: HVN
Context triple: [Tweed New Haven Airport, IATACode, HVN]
  • A. HVN
    HVN is the ICAO airline designator used to identify Vietnam Airlines in international aviation operations.
  • B. HVF
    HVF is a data-focused startup and innovation lab created by entrepreneur Max Levchin to explore and build companies around large-scale data problems.
  • C. VHP
    VHP is a right-wing Hindu nationalist organization in India known for its role in promoting Hindutva ideology and involvement in religious and political campaigns.
  • D. Hov
    Hov is a small village on the Faroe Islands' southernmost island of Suðuroy, known for its coastal setting and traditional Faroese character.
  • E. HAVA
    HAVA is the commonly used acronym for the Help America Vote Act, a U.S. federal law enacted to improve the administration and security of elections.
  • 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: HVN
Triple: [Tweed New Haven Airport, IATACode, HVN]
Generated description
HVN is the IATA airport code for Tweed New Haven Airport, a regional airport serving New Haven, Connecticut.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: HVN
Target entity description: HVN is the IATA airport code for Tweed New Haven Airport, a regional airport serving New Haven, Connecticut.
  • A. HVN
    HVN is the ICAO airline designator used to identify Vietnam Airlines in international aviation operations.
  • B. HVF
    HVF is a data-focused startup and innovation lab created by entrepreneur Max Levchin to explore and build companies around large-scale data problems.
  • C. VHP
    VHP is a right-wing Hindu nationalist organization in India known for its role in promoting Hindutva ideology and involvement in religious and political campaigns.
  • D. Hov
    Hov is a small village on the Faroe Islands' southernmost island of Suðuroy, known for its coastal setting and traditional Faroese character.
  • E. HAVA
    HAVA is the commonly used acronym for the Help America Vote Act, a U.S. federal law enacted to improve the administration and security of elections.
  • 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_69c00832aedc81909899801b141fa3b4 completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c0288a0ea8819091ac6f965471ceee completed March 22, 2026, 5:36 p.m.
NED1 Entity disambiguation (via context triple) batch_69c07e358d908190a37e5df89df3aedc completed March 22, 2026, 11:41 p.m.
NEDg Description generation batch_69c089020764819090a1927c65f9e870 completed March 23, 2026, 12:27 a.m.
NED2 Entity disambiguation (via description) batch_69c0897b75e481909adc413fa73e9496 completed March 23, 2026, 12:29 a.m.
Created at: March 22, 2026, 3:48 p.m.