Triple

T14352693
Position Surface form Disambiguated ID Type / Status
Subject Mustique Airport E355893 entity
Predicate IATAcode P418 FINISHED
Object MQS
MQS is the IATA airport code for Mustique Airport, which serves the private island of Mustique in Saint Vincent and the Grenadines.
E1096404 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: MQS | Statement: [Mustique Airport, IATAcode, MQS]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: MQS
Context triple: [Mustique Airport, IATAcode, MQS]
  • A. MQMs
    MQMs are Delta Air Lines’ status-qualifying miles that determine a SkyMiles member’s Medallion elite tier based on distance and fare class flown.
  • B. MQT
    MQT is the IATA airport code for Sawyer International Airport, a public airport serving the Marquette, Michigan area in the United States.
  • C. MQ
    MQ is the IATA airline designator used by American Eagle Airlines for its flight operations.
  • D. MQ
    MQ is IBM's messaging middleware that enables reliable, asynchronous communication between distributed applications and systems.
  • E. MQ
    MQ is a German vehicle registration code assigned to the Saalekreis district in the state of Saxony-Anhalt.
  • 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: MQS
Triple: [Mustique Airport, IATAcode, MQS]
Generated description
MQS is the IATA airport code for Mustique Airport, which serves the private island of Mustique in Saint Vincent and the Grenadines.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: MQS
Target entity description: MQS is the IATA airport code for Mustique Airport, which serves the private island of Mustique in Saint Vincent and the Grenadines.
  • A. MQMs
    MQMs are Delta Air Lines’ status-qualifying miles that determine a SkyMiles member’s Medallion elite tier based on distance and fare class flown.
  • B. MQT
    MQT is the IATA airport code for Sawyer International Airport, a public airport serving the Marquette, Michigan area in the United States.
  • C. MQ
    MQ is the IATA airline designator used by American Eagle Airlines for its flight operations.
  • D. MQ
    MQ is a German vehicle registration code assigned to the Saalekreis district in the state of Saxony-Anhalt.
  • E. MQ
    MQ is IBM's messaging middleware that enables reliable, asynchronous communication between distributed applications and systems.
  • 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_69d82790a7e08190877e2d349b2e8d8e completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de8f4ff1e48190bd9419d70098cede completed April 14, 2026, 7:02 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd4c44ff4c8190bbcc7a34b98ac330 completed May 8, 2026, 2:36 a.m.
NEDg Description generation batch_69fd512c32a081908e516c51d846a2c0 completed May 8, 2026, 2:57 a.m.
NED2 Entity disambiguation (via description) batch_69fd51e9a43c8190965bf0c7b5bbab26 completed May 8, 2026, 3 a.m.
Created at: April 10, 2026, 1:14 a.m.