Triple

T11870897
Position Surface form Disambiguated ID Type / Status
Subject Tainan Airport E282403 entity
Predicate IATAcode P418 FINISHED
Object TNN
TNN is the IATA airport code for Tainan Airport, a regional airport serving the city of Tainan in southern Taiwan.
 E951131 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: TNN | Statement: [Tainan Airport, IATAcode, TNN]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: TNN
Context triple: [Tainan Airport, IATAcode, TNN]
  • A. TNN
    TNN, originally known as The Nashville Network, was a U.S. cable television channel that evolved from country-music-focused programming into a broader general entertainment network before rebranding as Spike.
  • B. TN
    TN is the official two-letter U.S. Postal Service abbreviation for the state of Tennessee.
  • C. TN
    TN is the official vehicle registration code used for the Indian state of Tamil Nadu.
  • D. TN
    TN is a UK postcode area covering Tunbridge Wells and surrounding parts of Kent and East Sussex.
  • E. NTTA
    NTTA is the regional agency responsible for planning, building, operating, and maintaining toll roads and related transportation infrastructure in the North Texas area.
  • 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: TNN
Triple: [Tainan Airport, IATAcode, TNN]
Generated description
TNN is the IATA airport code for Tainan Airport, a regional airport serving the city of Tainan in southern Taiwan.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: TNN
Target entity description: TNN is the IATA airport code for Tainan Airport, a regional airport serving the city of Tainan in southern Taiwan.
  • A. TNN
    TNN, originally known as The Nashville Network, was a U.S. cable television channel that evolved from country-music-focused programming into a broader general entertainment network before rebranding as Spike.
  • B. TN
    TN is the official two-letter U.S. Postal Service abbreviation for the state of Tennessee.
  • C. TN
    TN is the official vehicle registration code used for the Indian state of Tamil Nadu.
  • D. TN
    TN is a UK postcode area covering Tunbridge Wells and surrounding parts of Kent and East Sussex.
  • E. NTTA
    NTTA is the regional agency responsible for planning, building, operating, and maintaining toll roads and related transportation infrastructure in the North Texas area.
  • 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_69d6ab2945d081908a5851c916cbcfb5 completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d8be15fb2481908f514781ce2c617f completed April 10, 2026, 9:08 a.m.
NED1 Entity disambiguation (via context triple) batch_69f281b0969c8190a8c0a01ca292cc84 completed April 29, 2026, 10:09 p.m.
NEDg Description generation batch_69f28a92ac90819092eef473a49d329e completed April 29, 2026, 10:47 p.m.
NED2 Entity disambiguation (via description) batch_69f28c462d888190a43e042b00921dbe completed April 29, 2026, 10:55 p.m.
Created at: April 8, 2026, 9:43 p.m.