Triple

T13976226
Position Surface form Disambiguated ID Type / Status
Subject Shimla Airport E336193 entity
Predicate ICAOcode P419 FINISHED
Object VISM
VISM is the ICAO airport code for Shimla Airport, a domestic airport serving the hill city of Shimla in Himachal Pradesh, India.
E1072739 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: VISM | Statement: [Shimla Airport, ICAOcode, VISM]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: VISM
Context triple: [Shimla Airport, ICAOcode, VISM]
  • A. VSM
    VSM is a post-nominal military decoration of India awarded for distinguished service of a high order to all ranks of the armed forces.
  • B. VSM
    VSM is the station code for Valley Stream station on the Long Island Rail Road in New York.
  • C. VSI
    VSI is the commonly used abbreviation for the "Very Short Introductions" series of concise, authoritative books published by Oxford University Press on a wide range of subjects.
  • D. VIS
    VIS is the IATA airport code for Visalia Municipal Airport in Visalia, California, United States.
  • E. VIS
    VIS is a large-scale European Union database system used to store and exchange visa application and related biometric data among member states’ authorities.
  • 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: VISM
Triple: [Shimla Airport, ICAOcode, VISM]
Generated description
VISM is the ICAO airport code for Shimla Airport, a domestic airport serving the hill city of Shimla in Himachal Pradesh, India.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: VISM
Target entity description: VISM is the ICAO airport code for Shimla Airport, a domestic airport serving the hill city of Shimla in Himachal Pradesh, India.
  • A. VSM
    VSM is the station code for Valley Stream station on the Long Island Rail Road in New York.
  • B. VSM
    VSM is a post-nominal military decoration of India awarded for distinguished service of a high order to all ranks of the armed forces.
  • C. VSI
    VSI is the commonly used abbreviation for the "Very Short Introductions" series of concise, authoritative books published by Oxford University Press on a wide range of subjects.
  • D. VIS
    VIS is a large-scale European Union database system used to store and exchange visa application and related biometric data among member states’ authorities.
  • E. VIS
    VIS is the IATA airport code for Visalia Municipal Airport in Visalia, California, United States.
  • 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_69d81c639e808190a0e4b4f3d31c6a59 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de2e90dc148190b38e339aac0de484 completed April 14, 2026, 12:09 p.m.
NED1 Entity disambiguation (via context triple) batch_69fba1e1eb108190b3c0739b94556172 completed May 6, 2026, 8:17 p.m.
NEDg Description generation batch_69fba5bff3b88190b5fcf3834e419b72 completed May 6, 2026, 8:34 p.m.
NED2 Entity disambiguation (via description) batch_69fba9af1e0c81908d4013410e76535a completed May 6, 2026, 8:50 p.m.
Created at: April 9, 2026, 10:18 p.m.