Triple

T22330915
Position Surface form Disambiguated ID Type / Status
Subject Ethiopian Airlines Flight 302 E552018 entity
Predicate aircraftRegistration P5244 FINISHED
Object ET-AVJ
ET-AVJ was the Boeing 737 MAX 8 aircraft operated by Ethiopian Airlines that crashed shortly after takeoff in 2019, leading to the global grounding of the 737 MAX fleet.
 E1531377 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: ET-AVJ | Statement: [Ethiopian Airlines Flight 302, aircraftRegistration, ET-AVJ]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: ET-AVJ
Context triple: [Ethiopian Airlines Flight 302, aircraftRegistration, ET-AVJ]
  • A. AVJ
    AVJ is the station code used to identify Peñón Viejo, a Mexico City Metro station on Line A.
  • B. ÁVH
    ÁVH was the secret police and state security organization of communist Hungary, notorious for its role in political repression and surveillance during the early Cold War era.
  • C. AV.
    AV. is the stock ticker symbol for Aviva plc, a major British multinational insurance, savings, and retirement services company listed on the London Stock Exchange.
  • D. AEV
    AEV is the common abbreviation for Augsburger Panther, a professional ice hockey club based in Augsburg, Germany.
  • E. AET
    AET is the former stock ticker symbol for Aetna Inc., a major U.S. health insurance and managed care company.
  • 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: ET-AVJ
Triple: [Ethiopian Airlines Flight 302, aircraftRegistration, ET-AVJ]
Generated description
ET-AVJ was the Boeing 737 MAX 8 aircraft operated by Ethiopian Airlines that crashed shortly after takeoff in 2019, leading to the global grounding of the 737 MAX fleet.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: ET-AVJ
Target entity description: ET-AVJ was the Boeing 737 MAX 8 aircraft operated by Ethiopian Airlines that crashed shortly after takeoff in 2019, leading to the global grounding of the 737 MAX fleet.
  • A. AVJ
    AVJ is the station code used to identify Peñón Viejo, a Mexico City Metro station on Line A.
  • B. ÁVH
    ÁVH was the secret police and state security organization of communist Hungary, notorious for its role in political repression and surveillance during the early Cold War era.
  • C. AV.
    AV. is the stock ticker symbol for Aviva plc, a major British multinational insurance, savings, and retirement services company listed on the London Stock Exchange.
  • D. AEV
    AEV is the common abbreviation for Augsburger Panther, a professional ice hockey club based in Augsburg, Germany.
  • E. AET
    AET is the former stock ticker symbol for Aetna Inc., a major U.S. health insurance and managed care company.
  • 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_69e11e482f788190b78d1588fc26d606 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f1577a9c348190b8662142afa832be completed April 29, 2026, 12:57 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0ad526a268819084cd7df7d7de1a23 completed May 18, 2026, 9 a.m.
NEDg Description generation batch_6a0ad992b43c8190b0e409d64db83308 completed May 18, 2026, 9:19 a.m.
NED2 Entity disambiguation (via description) batch_6a0adac48bec8190989dd7c5e28d283a completed May 18, 2026, 9:24 a.m.
Created at: April 16, 2026, 8:43 p.m.