Triple

T1549221
Position Surface form Disambiguated ID Type / Status
Subject Lorillard Tobacco Company E33048 entity
Predicate tickerSymbol P1447 FINISHED
Object LO
LO was the New York Stock Exchange ticker symbol for Lorillard Tobacco Company, a major American tobacco manufacturer best known for brands like Newport.
 E175756 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: LO | Statement: [Lorillard Tobacco Company, tickerSymbol, LO]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: LO
Context triple: [Lorillard Tobacco Company, tickerSymbol, LO]
  • A. LO
    LO is Norway’s largest and most influential trade union confederation, representing a broad spectrum of workers across multiple sectors.
  • B. L
    L is the enigmatic, emotionally complex protagonist of Hanne Ørstavik’s novel "Love," whose inner life and perspective drive the story’s exploration of isolation and longing.
  • C. L
    The L is a Chicago 'L' rapid transit line that serves the city’s West Side and western suburbs as part of the Chicago Transit Authority system.
  • D. LU
    LU is the two-letter ISO 3166-1 alpha-2 country code assigned to Luxembourg for international identification and data standards.
  • E. Le
    Le is a common Vietnamese surname shared by many notable figures in the country’s history and culture.
  • 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: LO
Triple: [Lorillard Tobacco Company, tickerSymbol, LO]
Generated description
LO was the New York Stock Exchange ticker symbol for Lorillard Tobacco Company, a major American tobacco manufacturer best known for brands like Newport.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: LO
Target entity description: LO was the New York Stock Exchange ticker symbol for Lorillard Tobacco Company, a major American tobacco manufacturer best known for brands like Newport.
  • A. LO
    LO is Norway’s largest and most influential trade union confederation, representing a broad spectrum of workers across multiple sectors.
  • B. L
    L is the enigmatic, emotionally complex protagonist of Hanne Ørstavik’s novel "Love," whose inner life and perspective drive the story’s exploration of isolation and longing.
  • C. L
    The L is a Chicago 'L' rapid transit line that serves the city’s West Side and western suburbs as part of the Chicago Transit Authority system.
  • D. LU
    LU is the two-letter ISO 3166-1 alpha-2 country code assigned to Luxembourg for international identification and data standards.
  • E. Le
    Le is a common Vietnamese surname shared by many notable figures in the country’s history and culture.
  • 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_69a885ee6db8819099502bc5ce8af881 completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69a90857bfb48190a2d66a601d228b72 completed March 5, 2026, 4:36 a.m.
NED1 Entity disambiguation (via context triple) batch_69ad30a29ae88190ab1b2ca97b8ed09c completed March 8, 2026, 8:17 a.m.
NEDg Description generation batch_69ad3196e92481909bd09e6c765a9698 completed March 8, 2026, 8:21 a.m.
NED2 Entity disambiguation (via description) batch_69ad32391ed881909826a80a90f18cb4 completed March 8, 2026, 8:24 a.m.
Created at: March 4, 2026, 7:26 p.m.