Triple

T43673
Position Surface form Disambiguated ID Type / Status
Subject George C. Marshall E859 entity
Predicate familyName P18 FINISHED
Object Marshall
Marshall is a common English surname borne by numerous notable figures, including military leaders, politicians, and artists.
 E16065 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: Marshall | Statement: [George C. Marshall, familyName, Marshall]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Marshall
Context triple: [George C. Marshall, familyName, Marshall]
  • A. Douglas
    Douglas is a masculine given name of Scottish origin that has been widely used in English-speaking countries.
  • B. Lawrence
    Lawrence is a historic mill city in northeastern Massachusetts that developed as a major textile manufacturing center along the Merrimack River.
  • C. Davis
    Davis is an underground rapid transit station in Somerville, Massachusetts, on Boston’s MBTA Red Line.
  • D. Winchester
    Winchester is a suburban town in Middlesex County, Massachusetts, known for its residential character and proximity to Boston.
  • E. Quincy
    Quincy is a coastal city in eastern Massachusetts known as the "City of Presidents" for being the birthplace of U.S. presidents John Adams and John Quincy Adams.
  • 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: Marshall
Triple: [George C. Marshall, familyName, Marshall]
Generated description
Marshall is a common English surname borne by numerous notable figures, including military leaders, politicians, and artists.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Marshall
Target entity description: Marshall is a common English surname borne by numerous notable figures, including military leaders, politicians, and artists.
  • A. Douglas
    Douglas is a masculine given name of Scottish origin that has been widely used in English-speaking countries.
  • B. Lawrence
    Lawrence is a historic mill city in northeastern Massachusetts that developed as a major textile manufacturing center along the Merrimack River.
  • C. Davis
    Davis is an underground rapid transit station in Somerville, Massachusetts, on Boston’s MBTA Red Line.
  • D. Winchester
    Winchester is a suburban town in Middlesex County, Massachusetts, known for its residential character and proximity to Boston.
  • E. Quincy
    Quincy is a coastal city in eastern Massachusetts known as the "City of Presidents" for being the birthplace of U.S. presidents John Adams and John Quincy Adams.
  • 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_69a247a8f6c08190bac804906d62ed5a completed Feb. 28, 2026, 1:40 a.m.
NER Named-entity recognition batch_69a24ae36824819080e8336a3c9f9bf8 completed Feb. 28, 2026, 1:54 a.m.
NED1 Entity disambiguation (via context triple) batch_69a2b4b65e0881908e82b8e3a4bd3aa4 completed Feb. 28, 2026, 9:26 a.m.
NEDg Description generation batch_69a2b4ff2c408190899d7570fc0745bd completed Feb. 28, 2026, 9:27 a.m.
NED2 Entity disambiguation (via description) batch_69a2b55aa8e48190ab8f93e6230071e0 completed Feb. 28, 2026, 9:28 a.m.
Created at: Feb. 28, 2026, 1:46 a.m.