Triple

T10703765
Position Surface form Disambiguated ID Type / Status
Subject Breguet Atlantique 2 E252346 entity
Predicate alsoKnownAs P39 FINISHED
Object ATL2
ATL2 is a French Breguet Atlantique 2 maritime patrol and anti-submarine warfare aircraft used primarily by the French Navy.
 E880309 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: ATL2 | Statement: [Breguet Atlantique 2, alsoKnownAs, ATL2]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: ATL2
Context triple: [Breguet Atlantique 2, alsoKnownAs, ATL2]
  • A. ATLC
    ATLC is the station code for the Atlantic City Rail Terminal, a key passenger rail hub in Atlantic City, New Jersey.
  • B. ATN
    ATN most likely refers to Augmented Transition Network, a type of finite state machine used in computational linguistics and natural language processing for parsing sentences.
  • C. ATN
    ATN is the fictional conservative cable news network owned by media mogul Logan Roy in the television series "Succession."
  • D. Exatel
    Exatel is a major Polish telecommunications company that operates one of the country’s key fiber-optic backbone networks and provides a range of data, internet, and cybersecurity services.
  • E. ATL
    ATL (Active Template Library) is a set of C++ templates from Microsoft used to simplify the creation of COM components and ActiveX controls, particularly for lightweight, high-performance Windows applications.
  • 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: ATL2
Triple: [Breguet Atlantique 2, alsoKnownAs, ATL2]
Generated description
ATL2 is a French Breguet Atlantique 2 maritime patrol and anti-submarine warfare aircraft used primarily by the French Navy.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: ATL2
Target entity description: ATL2 is a French Breguet Atlantique 2 maritime patrol and anti-submarine warfare aircraft used primarily by the French Navy.
  • A. ATLC
    ATLC is the station code for the Atlantic City Rail Terminal, a key passenger rail hub in Atlantic City, New Jersey.
  • B. ATN
    ATN most likely refers to Augmented Transition Network, a type of finite state machine used in computational linguistics and natural language processing for parsing sentences.
  • C. ATN
    ATN is the fictional conservative cable news network owned by media mogul Logan Roy in the television series "Succession."
  • D. Exatel
    Exatel is a major Polish telecommunications company that operates one of the country’s key fiber-optic backbone networks and provides a range of data, internet, and cybersecurity services.
  • E. ATL
    ATL (Active Template Library) is a set of C++ templates from Microsoft used to simplify the creation of COM components and ActiveX controls, particularly for lightweight, high-performance Windows applications.
  • 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_69d6aa5cbabc8190973e683950d89faf completed April 8, 2026, 7:19 p.m.
NER Named-entity recognition batch_69d6fdddf258819097b9fd26d68cd2e4 completed April 9, 2026, 1:16 a.m.
NED1 Entity disambiguation (via context triple) batch_69d998f5cda081909932daa3c98f8b46 completed April 11, 2026, 12:42 a.m.
NEDg Description generation batch_69d99e8632688190b3746649a124ca09 completed April 11, 2026, 1:06 a.m.
NED2 Entity disambiguation (via description) batch_69da625a1e8c8190b282e7a70bb7c876 completed April 11, 2026, 3:01 p.m.
Created at: April 8, 2026, 9:12 p.m.