Triple

T16251444
Position Surface form Disambiguated ID Type / Status
Subject Marsico Lung Institute E394513 entity
Predicate abbreviation P43 FINISHED
Object MLI
MLI is the commonly used abbreviation for the Marsico Lung Institute, a research center focused on lung biology and respiratory diseases.
E1202451 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: MLI | Statement: [Marsico Lung Institute, abbreviation, MLI]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: MLI
Context triple: [Marsico Lung Institute, abbreviation, MLI]
  • A. MLI
    MLI is the three-letter ISO 3166-1 alpha-3 country code assigned to Mali.
  • B. MLI
    MLI is the IATA airport code for Quad Cities International Airport serving the Quad Cities region in Illinois and Iowa, United States.
  • C. ML-2
    ML-2 is a major north–south railway corridor in Pakistan that serves as one of the country’s principal main lines parallel to the primary ML-1 route.
  • D. ML-1
    ML-1 is Pakistan Railways’ primary north–south main line, connecting major cities and serving as the backbone of the country’s rail transport system.
  • E. MSL
    MSL is a NASA mission featuring the Curiosity rover, designed to explore Mars’ surface and assess its past and present habitability.
  • 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: MLI
Triple: [Marsico Lung Institute, abbreviation, MLI]
Generated description
MLI is the commonly used abbreviation for the Marsico Lung Institute, a research center focused on lung biology and respiratory diseases.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: MLI
Target entity description: MLI is the commonly used abbreviation for the Marsico Lung Institute, a research center focused on lung biology and respiratory diseases.
  • A. MLI
    MLI is the three-letter ISO 3166-1 alpha-3 country code assigned to Mali.
  • B. MLI
    MLI is the IATA airport code for Quad Cities International Airport serving the Quad Cities region in Illinois and Iowa, United States.
  • C. ML-2
    ML-2 is a major north–south railway corridor in Pakistan that serves as one of the country’s principal main lines parallel to the primary ML-1 route.
  • D. ML-1
    ML-1 is Pakistan Railways’ primary north–south main line, connecting major cities and serving as the backbone of the country’s rail transport system.
  • E. MSL
    MSL is a NASA mission featuring the Curiosity rover, designed to explore Mars’ surface and assess its past and present habitability.
  • 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_69d87f2171208190951025e526947816 completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e24596e2208190ad9d9abfa6620ca1 completed April 17, 2026, 2:37 p.m.
NED1 Entity disambiguation (via context triple) batch_6a000ee568a48190835ce76f84461044 completed May 10, 2026, 4:51 a.m.
NEDg Description generation batch_6a0011995ff481908bbca9f9cfb41bf0 completed May 10, 2026, 5:03 a.m.
NED2 Entity disambiguation (via description) batch_6a0012669ff48190884367b92962a6d4 completed May 10, 2026, 5:06 a.m.
Created at: April 10, 2026, 5:04 a.m.