Triple

T14757756
Position Surface form Disambiguated ID Type / Status
Subject Herbert Ross E346774 entity
Predicate familyName P18 FINISHED
Object Ross
Ross is a common surname of Scottish and English origin borne by numerous notable figures across fields such as entertainment, politics, and sports.
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: [Herbert Ross, familyName, Ross]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ross
Context triple: [Herbert Ross, familyName, Ross]
  • A. John
    John is the husband of Martha Rainsborough.
  • B. John
    John is the given name of John Henry Patterson, an American industrialist and founder of the National Cash Register Company.
  • C. 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.
  • D. John
    John is the given name of Sir John Woodville, a 15th-century English nobleman associated with the influential Woodville family during the Wars of the Roses.
  • E. John
    John is the given name of John Sharp, who served as the Archbishop of York in the Church of England during the late 17th and early 18th centuries.
  • 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: [Herbert Ross, familyName, Ross]
Generated description
Ross is a common surname of Scottish and English origin borne by numerous notable figures across fields such as entertainment, politics, and sports.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Ross
Target entity description: Ross is a common surname of Scottish and English origin borne by numerous notable figures across fields such as entertainment, politics, and sports.
  • 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. John
    John is the husband of Martha Rainsborough.
  • E. John
    John is the given name of John Henry Patterson, an American industrialist and founder of the National Cash Register Company.
  • 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_69d822e8896c819091169882f9b20486 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69dec7f0f5a48190af008352c26574d7 completed April 14, 2026, 11:04 p.m.
NED1 Entity disambiguation (via context triple) batch_69fe0ced0e2c8190a13e3b43e4d35560 completed May 8, 2026, 4:18 p.m.
NEDg Description generation batch_69fe15f78180819088c7be010ef27029 completed May 8, 2026, 4:57 p.m.
NED2 Entity disambiguation (via description) batch_69fe165c1f188190963f9b78272f41f7 completed May 8, 2026, 4:59 p.m.
Created at: April 10, 2026, 1:30 a.m.