Triple

T488482
Position Surface form Disambiguated ID Type / Status
Subject Dan Snyder E9932 entity
Predicate familyName P18 FINISHED
Object Snyder
Snyder is a surname most prominently associated with Dan Snyder, the American businessman and former owner of the NFL’s Washington Commanders.
 E61047 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: Snyder | Statement: [Dan Snyder, familyName, Snyder]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Snyder
Context triple: [Dan Snyder, familyName, Snyder]
  • A. Nolan
    Nolan is a common Irish surname that has been borne by numerous notable figures across fields such as film, sports, and politics.
  • B. Sullivan
    Sullivan is a shortened name for the international law firm Sullivan & Worcester LLP, known for its corporate, tax, and financial legal services.
  • C. Miller
    Miller is a common English and Scottish occupational surname historically given to people who worked in grain mills.
  • D. Smith
    Smith is a common English surname borne by numerous notable individuals across diverse fields such as politics, arts, sports, and academia.
  • E. Fink
    Fink is an open-source package management system that brings a wide range of Unix and open-source software to macOS by compiling and distributing it in a convenient, Debian-like format.
  • 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: Snyder
Triple: [Dan Snyder, familyName, Snyder]
Generated description
Snyder is a surname most prominently associated with Dan Snyder, the American businessman and former owner of the NFL’s Washington Commanders.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Snyder
Target entity description: Snyder is a surname most prominently associated with Dan Snyder, the American businessman and former owner of the NFL’s Washington Commanders.
  • A. Nolan
    Nolan is a common Irish surname that has been borne by numerous notable figures across fields such as film, sports, and politics.
  • B. Sullivan
    Sullivan is a shortened name for the international law firm Sullivan & Worcester LLP, known for its corporate, tax, and financial legal services.
  • C. Miller
    Miller is a common English and Scottish occupational surname historically given to people who worked in grain mills.
  • D. Smith
    Smith is a common English surname borne by numerous notable individuals across diverse fields such as politics, arts, sports, and academia.
  • E. Fink
    Fink is an open-source package management system that brings a wide range of Unix and open-source software to macOS by compiling and distributing it in a convenient, Debian-like format.
  • 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_69a2e802e2908190ab17c9479e0b6412 completed Feb. 28, 2026, 1:05 p.m.
NER Named-entity recognition batch_69a2f0df764481909811d9483dfbc4aa completed Feb. 28, 2026, 1:42 p.m.
NED1 Entity disambiguation (via context triple) batch_69a47471e5ac8190acfed4803183f11a completed March 1, 2026, 5:16 p.m.
NEDg Description generation batch_69a476527a6881909cc06330ae6bcbcb completed March 1, 2026, 5:24 p.m.
NED2 Entity disambiguation (via description) batch_69a4769c31f081909bc74682ed6fd9d6 completed March 1, 2026, 5:25 p.m.
Created at: Feb. 28, 2026, 1:12 p.m.