Triple

T21728765
Position Surface form Disambiguated ID Type / Status
Subject Watertown International Airport E536342 entity
Predicate IATAcode P418 FINISHED
Object ART
ART is the three-letter IATA airport code assigned to Watertown International Airport in New York, United States.
 E1499176 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: ART | Statement: [Watertown International Airport, IATAcode, ART]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: ART
Context triple: [Watertown International Airport, IATAcode, ART]
  • A. ART
    ART is a famous pop art sculpture by Robert Indiana that features the word "ART" in bold, stacked letters, echoing the style of his iconic LOVE works.
  • B. ART
    ART is the commonly used abbreviation for the Artland Dragons, a professional basketball team based in Quakenbrück, Germany.
  • C. ART
    ART is the bus rapid transit system serving Albuquerque, New Mexico, designed to provide faster and more efficient public transportation along key corridors in the city.
  • D. ART
    ART is a renowned professional theater company based in Cambridge, Massachusetts, known for its innovative and experimental productions and its affiliation with Harvard University.
  • E. ART
    ART is the managed runtime environment used by the Android operating system to execute applications, providing ahead-of-time and just-in-time compilation, garbage collection, and other core execution services.
  • 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: ART
Triple: [Watertown International Airport, IATAcode, ART]
Generated description
ART is the three-letter IATA airport code assigned to Watertown International Airport in New York, United States.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: ART
Target entity description: ART is the three-letter IATA airport code assigned to Watertown International Airport in New York, United States.
  • A. ART
    ART is a renowned professional theater company based in Cambridge, Massachusetts, known for its innovative and experimental productions and its affiliation with Harvard University.
  • B. ART
    ART is the commonly used abbreviation for the Artland Dragons, a professional basketball team based in Quakenbrück, Germany.
  • C. ART
    ART is the bus rapid transit system serving Albuquerque, New Mexico, designed to provide faster and more efficient public transportation along key corridors in the city.
  • D. ART
    ART is a famous pop art sculpture by Robert Indiana that features the word "ART" in bold, stacked letters, echoing the style of his iconic LOVE works.
  • E. ART
    ART is a specialized field focused on developing and applying computing techniques for real-time systems and practical applications.
  • 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_69e0c46d3284819099a4f9d5a704eb95 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69effd04c9648190922e8fa7c74ac1b5 completed April 28, 2026, 12:19 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0a2ecc31948190848c6e01ea121deb completed May 17, 2026, 9:10 p.m.
NEDg Description generation batch_6a0a2fd17bd48190a6ba7a80b244cdd7 completed May 17, 2026, 9:14 p.m.
NED2 Entity disambiguation (via description) batch_6a0a3047eb04819082e2b9f4e62b4b0b completed May 17, 2026, 9:16 p.m.
Created at: April 16, 2026, 6:48 p.m.