Triple

T18927869
Position Surface form Disambiguated ID Type / Status
Subject John Ross E463020 entity
Predicate familyName P18 FINISHED
Object Ross
Ross is a common Scottish-origin surname borne by numerous notable figures across politics, sports, arts, and academia.
E87043 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: Ross | Statement: [John Ross, familyName, Ross]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ross
Context triple: [John Ross, familyName, Ross]
  • A. John
    John B. Magruder was a Confederate major general during the American Civil War, known for his leadership in the Peninsula Campaign and his flamboyant personality.
  • B. John
    John is the given name of John Vlissides, a software engineer best known as one of the “Gang of Four” authors of the influential book *Design Patterns: Elements of Reusable Object-Oriented Software*.
  • C. John
    John is a fictional police detective and main character from the science fiction TV series "Almost Human."
  • D. John
    John of Brienne was a 13th-century French nobleman who served as Grand Butler of France and played a prominent role in the kingdom’s courtly and political life.
  • E. John
    John Warham was a New Zealand ornithologist and photographer known for his pioneering studies of seabirds, particularly petrels and penguins.
  • 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: Ross
Triple: [John Ross, familyName, Ross]
Generated description
Ross is a common Scottish-origin surname borne by numerous notable figures across politics, sports, arts, and academia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Ross
Target entity description: Ross is a common Scottish-origin surname borne by numerous notable figures across politics, sports, arts, and academia.
  • A. Ross chosen
    Ross is a common Scottish-origin surname borne by numerous notable figures across fields such as politics, science, arts, and sports.
  • B. Ross
    Ross is a small, affluent residential town in Marin County, California, known for its wooded setting and quiet, upscale character.
  • C. Ross
    Ross is a historic region in the Scottish Highlands traditionally associated with Clan Ross and known for its rugged landscapes and coastal scenery.
  • D. Ross
    Ross is a masculine given name of Scottish and English origin, commonly used in English-speaking countries.
  • E. Ross
    Ross is a historic episcopal see in Ireland that forms part of the united Church of Ireland Diocese of Cork, Cloyne and Ross.
  • F. None of above.

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_69d8dcfdbbb881909964fa5a75bd0b48 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5c9bdddb481908bebd32f927ed5de completed April 20, 2026, 6:37 a.m.
NED1 Entity disambiguation (via context triple) batch_6a05911dd02c81909ea050471cc7774a completed May 14, 2026, 9:08 a.m.
NEDg Description generation batch_6a05935f68bc819084d1f46fd9d51a2e completed May 14, 2026, 9:18 a.m.
NED2 Entity disambiguation (via description) batch_6a05944851d48190827e1a7fe9a795d5 completed May 14, 2026, 9:22 a.m.
Created at: April 10, 2026, 11:59 a.m.