Triple

T10341846
Position Surface form Disambiguated ID Type / Status
Subject Visa Information System E243144 entity
Predicate abbreviation P43 FINISHED
Object 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.
 E858301 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: VIS | Statement: [Visa Information System, abbreviation, VIS]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: VIS
Context triple: [Visa Information System, abbreviation, VIS]
  • A. VIS
    VIS is the IATA airport code for Visalia Municipal Airport in Visalia, California, United States.
  • B. Vis
    Vis is a Croatian island in the Adriatic Sea known for its unspoiled nature, historic towns, and former role as a strategic military base.
  • C. VISIR
    VISIR is a mid-infrared imager and spectrometer used on ESO’s Very Large Telescope to study celestial objects at thermal infrared wavelengths.
  • D. 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.
  • E. VES
    VES is an abbreviation for the Virtual Execution System, a runtime environment designed to execute managed code in a platform-independent manner.
  • 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: VIS
Triple: [Visa Information System, abbreviation, VIS]
Generated description
VIS is a large-scale European Union database system used to store and exchange visa application and related biometric data among member states’ authorities.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: VIS
Target entity description: VIS is a large-scale European Union database system used to store and exchange visa application and related biometric data among member states’ authorities.
  • A. VIS
    VIS is the IATA airport code for Visalia Municipal Airport in Visalia, California, United States.
  • B. Vis
    Vis is a Croatian island in the Adriatic Sea known for its unspoiled nature, historic towns, and former role as a strategic military base.
  • C. VISIR
    VISIR is a mid-infrared imager and spectrometer used on ESO’s Very Large Telescope to study celestial objects at thermal infrared wavelengths.
  • D. 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.
  • E. VES
    VES is an abbreviation for the Virtual Execution System, a runtime environment designed to execute managed code in a platform-independent manner.
  • 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_69d381af787481908bc401325c760a88 completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4e0a645348190af91450360a9abed completed April 7, 2026, 10:47 a.m.
NED1 Entity disambiguation (via context triple) batch_69d75070c3ac8190b0d50a93d48c9bd9 completed April 9, 2026, 7:08 a.m.
NEDg Description generation batch_69d7618c9abc819080c4d6669dfb8320 completed April 9, 2026, 8:21 a.m.
NED2 Entity disambiguation (via description) batch_69d7702ae24481908b0f5319413e81d4 completed April 9, 2026, 9:23 a.m.
Created at: April 6, 2026, 11:55 a.m.