Triple

T9445012
Position Surface form Disambiguated ID Type / Status
Subject Spriggs Payne Airport E227741 entity
Predicate IATAcode P418 FINISHED
Object MLW
MLW is the IATA airport code for Spriggs Payne Airport in Monrovia, Liberia.
 E799200 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: MLW | Statement: [Spriggs Payne Airport, IATAcode, MLW]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: MLW
Context triple: [Spriggs Payne Airport, IATAcode, MLW]
  • A. MCWL
    MCWL is the U.S. Marine Corps Warfighting Laboratory, responsible for developing, testing, and integrating innovative concepts and technologies to enhance future Marine Corps combat capabilities.
  • B. WE League
    WE League is Japan’s professional women’s football league, established to promote and develop elite women’s soccer in the country.
  • C. MPL
    MPL is the IATA airport code for Montpellier-Méditerranée Airport, serving the city of Montpellier in southern France.
  • D. MPL
    MPL (Mozilla Public License) is a free and open-source software license created by Mozilla that allows code to be shared and modified while requiring that changes to MPL-covered files remain publicly available.
  • E. WWC
    WWC is a U.S. Department of Education initiative that reviews and summarizes research evidence on educational programs, practices, and policies to inform educators and policymakers.
  • 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: MLW
Triple: [Spriggs Payne Airport, IATAcode, MLW]
Generated description
MLW is the IATA airport code for Spriggs Payne Airport in Monrovia, Liberia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: MLW
Target entity description: MLW is the IATA airport code for Spriggs Payne Airport in Monrovia, Liberia.
  • A. MCWL
    MCWL is the U.S. Marine Corps Warfighting Laboratory, responsible for developing, testing, and integrating innovative concepts and technologies to enhance future Marine Corps combat capabilities.
  • B. WE League
    WE League is Japan’s professional women’s football league, established to promote and develop elite women’s soccer in the country.
  • C. MPL
    MPL is the IATA airport code for Montpellier-Méditerranée Airport, serving the city of Montpellier in southern France.
  • D. MPL
    MPL (Mozilla Public License) is a free and open-source software license created by Mozilla that allows code to be shared and modified while requiring that changes to MPL-covered files remain publicly available.
  • E. WWC
    WWC is a U.S. Department of Education initiative that reviews and summarizes research evidence on educational programs, practices, and policies to inform educators and policymakers.
  • 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_69ca843884488190ad6cbe0153088234 completed March 30, 2026, 2:10 p.m.
NER Named-entity recognition batch_69cd7f32aee88190a43573f97fa1e49d completed April 1, 2026, 8:25 p.m.
NED1 Entity disambiguation (via context triple) batch_69d110669ca48190bbaf772e2e6aa457 completed April 4, 2026, 1:21 p.m.
NEDg Description generation batch_69d110eeddc881908661d110269b8a1c completed April 4, 2026, 1:23 p.m.
NED2 Entity disambiguation (via description) batch_69d111f3190c8190ba2fe5687212da25 completed April 4, 2026, 1:28 p.m.
Created at: March 30, 2026, 7:51 p.m.