Triple

T16038765
Position Surface form Disambiguated ID Type / Status
Subject Angelica Ross E389037 entity
Predicate familyName P18 FINISHED
Object Ross
Ross is a common English and Scottish surname borne by numerous notable individuals across entertainment, politics, sports, and other fields.
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: [Angelica Ross, familyName, Ross]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ross
Context triple: [Angelica Ross, familyName, Ross]
  • A. John
    John is the first name of J. Michael Luttig, a prominent American conservative jurist and former federal appellate judge.
  • B. 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.
  • C. John
    John is the given name of Prince Alexander John of Wales, a short-lived British royal infant of the 19th century.
  • 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 André, the British Army officer and spymaster during the American Revolutionary War who was executed for his role in Benedict Arnold’s treason.
  • 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: [Angelica Ross, familyName, Ross]
Generated description
Ross is a common English and Scottish surname borne by numerous notable individuals across entertainment, politics, sports, and other fields.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Ross
Target entity description: Ross is a common English and Scottish surname borne by numerous notable individuals across entertainment, politics, sports, and other fields.
  • 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. John
    John is the first name of J. Michael Luttig, a prominent American conservative jurist and former federal appellate judge.
  • 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_69d86dada3808190825d5f80d72fbe88 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e1833eb90c8190b10dca3ce0793ddf completed April 17, 2026, 12:47 a.m.
NED1 Entity disambiguation (via context triple) batch_69ffdbd5acb48190a10e40074fffd425 completed May 10, 2026, 1:13 a.m.
NEDg Description generation batch_69ffdd527cfc8190a616a2334edffd02 completed May 10, 2026, 1:20 a.m.
NED2 Entity disambiguation (via description) batch_69ffdda1a0908190b7c880c5d66f7400 completed May 10, 2026, 1:21 a.m.
Created at: April 10, 2026, 4:56 a.m.