Triple

T12899133
Position Surface form Disambiguated ID Type / Status
Subject LaTeX3 E308570 entity
Predicate hasComponent P35 FINISHED
Object l3kernel
l3kernel is the core programming layer of LaTeX3, providing the fundamental macros and data structures on which higher-level LaTeX3 code is built.
E1008093 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: l3kernel | Statement: [LaTeX3, hasComponent, l3kernel]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: l3kernel
Context triple: [LaTeX3, hasComponent, l3kernel]
  • A. L3
    L3 is a particle physics experiment that operated at CERN’s Large Electron–Positron Collider, designed to study high-energy electron–positron collisions and probe the Standard Model.
  • B. L3
    L3 is one of the main lines of the Barcelona Metro rapid transit system.
  • C. KERNAL
    KERNAL is the low-level operating system and I/O firmware of Commodore 8-bit computers, providing core routines for hardware access and system services.
  • D. LKO
    LKO is the IATA airport code for Chaudhary Charan Singh International Airport serving Lucknow, India.
  • E. Lively Kernel
    Lively Kernel is a web-based, live programming environment and platform for building and manipulating graphical applications directly in the browser using JavaScript and SVG.
  • 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: l3kernel
Triple: [LaTeX3, hasComponent, l3kernel]
Generated description
l3kernel is the core programming layer of LaTeX3, providing the fundamental macros and data structures on which higher-level LaTeX3 code is built.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: l3kernel
Target entity description: l3kernel is the core programming layer of LaTeX3, providing the fundamental macros and data structures on which higher-level LaTeX3 code is built.
  • A. L3
    L3 is a particle physics experiment that operated at CERN’s Large Electron–Positron Collider, designed to study high-energy electron–positron collisions and probe the Standard Model.
  • B. L3
    L3 is one of the main lines of the Barcelona Metro rapid transit system.
  • C. KERNAL
    KERNAL is the low-level operating system and I/O firmware of Commodore 8-bit computers, providing core routines for hardware access and system services.
  • D. LKO
    LKO is the IATA airport code for Chaudhary Charan Singh International Airport serving Lucknow, India.
  • E. Lively Kernel
    Lively Kernel is a web-based, live programming environment and platform for building and manipulating graphical applications directly in the browser using JavaScript and SVG.
  • 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_69d7bdf7c1f0819098102569a8d8cbf5 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d9717f3fc48190b61c8f6f36cd0725 completed April 10, 2026, 9:54 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6a56189b081909ed838addcb6d265 completed May 3, 2026, 1:31 a.m.
NEDg Description generation batch_69f6a6179cdc8190976daa1384032445 completed May 3, 2026, 1:34 a.m.
NED2 Entity disambiguation (via description) batch_69f6a6cbec348190a96a0194b2d6be4b completed May 3, 2026, 1:37 a.m.
Created at: April 9, 2026, 5:40 p.m.