Triple

T2978182
Position Surface form Disambiguated ID Type / Status
Subject Jaguar E80447 entity
Predicate founders P104 FINISHED
Object William Lyons
William Lyons was a British automobile manufacturer and entrepreneur best known for co-founding and leading Jaguar Cars to international prominence.
 E318278 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: William Lyons | Statement: [Jaguar, founders, William Lyons]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: William Lyons
Context triple: [Jaguar, founders, William Lyons]
  • A. John Lyons
    John Lyons is a film producer best known for his work on major Hollywood comedies, including the Austin Powers series.
  • B. Lloyd Robertson
    Lloyd Robertson is a prominent Canadian television journalist and longtime national news anchor best known for his decades of work with CTV News.
  • C. Ralph Miller
    Ralph Miller was a highly respected American college basketball coach best known for transforming Oregon State University into a national contender during his long tenure.
  • D. Cecil Carstenson
    Cecil Carstenson was an American sculptor best known for his modernist wood carvings and contributions to mid-20th-century art.
  • E. William Osborne
    William Osborne is a British screenwriter best known for co-writing the 1992 action-comedy film "Stop! Or My Mom Will Shoot."
  • 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: William Lyons
Triple: [Jaguar, founders, William Lyons]
Generated description
William Lyons was a British automobile manufacturer and entrepreneur best known for co-founding and leading Jaguar Cars to international prominence.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: William Lyons
Target entity description: William Lyons was a British automobile manufacturer and entrepreneur best known for co-founding and leading Jaguar Cars to international prominence.
  • A. John Lyons
    John Lyons is a film producer best known for his work on major Hollywood comedies, including the Austin Powers series.
  • B. Lloyd Robertson
    Lloyd Robertson is a prominent Canadian television journalist and longtime national news anchor best known for his decades of work with CTV News.
  • C. Ralph Miller
    Ralph Miller was a highly respected American college basketball coach best known for transforming Oregon State University into a national contender during his long tenure.
  • D. Cecil Carstenson
    Cecil Carstenson was an American sculptor best known for his modernist wood carvings and contributions to mid-20th-century art.
  • E. William Osborne
    William Osborne is a British screenwriter best known for co-writing the 1992 action-comedy film "Stop! Or My Mom Will Shoot."
  • 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_69ad8b15f6ac8190be5fd16a33edcb4f completed March 8, 2026, 2:43 p.m.
NER Named-entity recognition batch_69ad999b0d50819093dac7678b887a9b completed March 8, 2026, 3:45 p.m.
NED1 Entity disambiguation (via context triple) batch_69b12e2c498881909dc0349b56db5c87 completed March 11, 2026, 8:56 a.m.
NEDg Description generation batch_69b1320a28808190b0f751eb6f198795 completed March 11, 2026, 9:12 a.m.
NED2 Entity disambiguation (via description) batch_69b1cb35a0048190bad4b190eb710ec1 completed March 11, 2026, 8:06 p.m.
Created at: March 8, 2026, 2:58 p.m.