Triple

T15910540
Position Surface form Disambiguated ID Type / Status
Subject Graham Holdings Company E385835 entity
Predicate tickerSymbol P1447 FINISHED
Object GHC
GHC is the stock ticker symbol for Graham Holdings Company, a diversified American conglomerate with interests in education, media, and other businesses.
 E1183779 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: GHC | Statement: [Graham Holdings Company, tickerSymbol, GHC]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: GHC
Context triple: [Graham Holdings Company, tickerSymbol, GHC]
  • A. GHC
    GHC (Glasgow Haskell Compiler) is the most widely used, feature-rich, and optimizing compiler for the Haskell programming language.
  • B. GHC
    GHC is a leading international membership organization that advocates for improved global health policies and supports collaboration among health professionals, NGOs, and other stakeholders worldwide.
  • C. GHC
    GHC is the Gauhati High Court, the principal judicial authority for the Indian state of Assam and certain neighboring states in the Northeast region.
  • D. Haskell
    Haskell is a small town in Muskogee County, Oklahoma, known for its rural character and local community life.
  • E. Haskell
    Haskell is a statically typed, purely functional programming language known for its strong type system, lazy evaluation, and use in both academic research and industry.
  • 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: GHC
Triple: [Graham Holdings Company, tickerSymbol, GHC]
Generated description
GHC is the stock ticker symbol for Graham Holdings Company, a diversified American conglomerate with interests in education, media, and other businesses.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: GHC
Target entity description: GHC is the stock ticker symbol for Graham Holdings Company, a diversified American conglomerate with interests in education, media, and other businesses.
  • A. GHC
    GHC is the Gauhati High Court, the principal judicial authority for the Indian state of Assam and certain neighboring states in the Northeast region.
  • B. GHC
    GHC (Glasgow Haskell Compiler) is the most widely used, feature-rich, and optimizing compiler for the Haskell programming language.
  • C. GHC
    GHC is a leading international membership organization that advocates for improved global health policies and supports collaboration among health professionals, NGOs, and other stakeholders worldwide.
  • D. Haskell
    Haskell is a small town in Muskogee County, Oklahoma, known for its rural character and local community life.
  • E. Haskell
    Haskell is a statically typed, purely functional programming language known for its strong type system, lazy evaluation, and use in both academic research and industry.
  • 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_69d86da686e4819097cbf3b1fc2d881d completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e1565ea7a8819097efffda366b5245 completed April 16, 2026, 9:36 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffb05750ac81908860143f4ca26cc7 completed May 9, 2026, 10:08 p.m.
NEDg Description generation batch_69ffb110a5b88190904f763057e8eb1e completed May 9, 2026, 10:11 p.m.
NED2 Entity disambiguation (via description) batch_69ffb1a5e9b88190b790c81b9500c2ac completed May 9, 2026, 10:13 p.m.
Created at: April 10, 2026, 4:52 a.m.