Triple

T14539117
Position Surface form Disambiguated ID Type / Status
Subject eBPF E341122 entity
Predicate usedBy P260 FINISHED
Object Katran
Katran is a high-performance, open-source layer 4 load balancer developed by Meta that leverages eBPF for efficient packet processing in large-scale network infrastructures.
E1103993 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: Katran | Statement: [eBPF, usedBy, Katran]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Katran
Context triple: [eBPF, usedBy, Katran]
  • A. Krewo
    Krewo is a historic village in present-day Belarus, best known as the site where the Union of Krewo was concluded in 1385, marking a pivotal dynastic union between the Kingdom of Poland and the Grand Duchy of Lithuania.
  • B. Krupa
    Krupa is a surname most famously associated with Gene Krupa, the pioneering American jazz and big band drummer.
  • C. Stryama
    Stryama is a river in Bulgaria that flows through the central part of the country before joining the Maritsa River.
  • D. Kusttram
    Kusttram is a Belgian coastal tram service that runs the length of the country’s North Sea shoreline, connecting numerous seaside towns and resorts.
  • E. Karatz
    Karatz is a surname most notably associated with Bruce Karatz, an American businessman and former CEO of homebuilding company KB Home.
  • 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: Katran
Triple: [eBPF, usedBy, Katran]
Generated description
Katran is a high-performance, open-source layer 4 load balancer developed by Meta that leverages eBPF for efficient packet processing in large-scale network infrastructures.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Katran
Target entity description: Katran is a high-performance, open-source layer 4 load balancer developed by Meta that leverages eBPF for efficient packet processing in large-scale network infrastructures.
  • A. Krewo
    Krewo is a historic village in present-day Belarus, best known as the site where the Union of Krewo was concluded in 1385, marking a pivotal dynastic union between the Kingdom of Poland and the Grand Duchy of Lithuania.
  • B. Krupa
    Krupa is a surname most famously associated with Gene Krupa, the pioneering American jazz and big band drummer.
  • C. Stryama
    Stryama is a river in Bulgaria that flows through the central part of the country before joining the Maritsa River.
  • D. Kusttram
    Kusttram is a Belgian coastal tram service that runs the length of the country’s North Sea shoreline, connecting numerous seaside towns and resorts.
  • E. Karatz
    Karatz is a surname most notably associated with Bruce Karatz, an American businessman and former CEO of homebuilding company KB Home.
  • 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_69d822dac79c8190a84a073f3cbaced5 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69deb1bb90008190947ac0961393446d completed April 14, 2026, 9:29 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd7a5cca788190aa8762d860c78721 completed May 8, 2026, 5:53 a.m.
NEDg Description generation batch_69fd7b1452d48190b95187cc6b6e5b6a completed May 8, 2026, 5:56 a.m.
NED2 Entity disambiguation (via description) batch_69fd7b9387988190abb20ea06c04d6cc completed May 8, 2026, 5:58 a.m.
Created at: April 10, 2026, 1:22 a.m.