Triple

T8265365
Position Surface form Disambiguated ID Type / Status
Subject Velana International Airport E193288 entity
Predicate IATAcode P418 FINISHED
Object MLE
MLE is the IATA airport code for Velana International Airport, the main international gateway to the Maldives located near the capital city Malé.
E722131 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: MLE | Statement: [Velana International Airport, IATAcode, MLE]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: MLE
Context triple: [Velana International Airport, IATAcode, MLE]
  • A. ML
    ML is the postcode area in central Scotland that covers Motherwell and surrounding towns.
  • B. ML
    ML is a post-nominal honorific indicating a recipient of Papua New Guinea’s Order of Logohu, a national order of merit.
  • C. ML
    ML is a statically typed functional programming language developed at the University of Edinburgh, known for pioneering features like type inference, pattern matching, and modules that strongly influenced later languages such as Elm, Haskell, and OCaml.
  • D. Helmholtz machine
    The Helmholtz machine is a pioneering generative neural network model that learns internal representations by using separate recognition and generative pathways to perform unsupervised learning.
  • E. Gaussian mixture models
    Gaussian mixture models are probabilistic clustering models that represent data as a combination of multiple Gaussian distributions, allowing soft cluster assignments and more flexible cluster shapes than KMeans.
  • 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: MLE
Triple: [Velana International Airport, IATAcode, MLE]
Generated description
MLE is the IATA airport code for Velana International Airport, the main international gateway to the Maldives located near the capital city Malé.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: MLE
Target entity description: MLE is the IATA airport code for Velana International Airport, the main international gateway to the Maldives located near the capital city Malé.
  • A. ML
    ML is the postcode area in central Scotland that covers Motherwell and surrounding towns.
  • B. ML
    ML is a statically typed functional programming language developed at the University of Edinburgh, known for pioneering features like type inference, pattern matching, and modules that strongly influenced later languages such as Elm, Haskell, and OCaml.
  • C. ML
    ML is a post-nominal honorific indicating a recipient of Papua New Guinea’s Order of Logohu, a national order of merit.
  • D. Helmholtz machine
    The Helmholtz machine is a pioneering generative neural network model that learns internal representations by using separate recognition and generative pathways to perform unsupervised learning.
  • E. Gaussian mixture models
    Gaussian mixture models are probabilistic clustering models that represent data as a combination of multiple Gaussian distributions, allowing soft cluster assignments and more flexible cluster shapes than KMeans.
  • 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_69ca82e081d48190986beaa51f498ab9 completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cb794c54448190a685b8d0070980d7 completed March 31, 2026, 7:35 a.m.
NED1 Entity disambiguation (via context triple) batch_69cd357b0ae081909fdaeab31624e6f1 completed April 1, 2026, 3:10 p.m.
NEDg Description generation batch_69cd4e5e9a2c819099a65053a12c8fde completed April 1, 2026, 4:57 p.m.
NED2 Entity disambiguation (via description) batch_69cd507ce2a881909da6871a9f6df119 completed April 1, 2026, 5:06 p.m.
Created at: March 30, 2026, 5:50 p.m.