Triple

T10552766
Position Surface form Disambiguated ID Type / Status
Subject SeatGeek E248994 entity
Predicate foundedBy P104 FINISHED
Object Eric Waller
Eric Waller is an entrepreneur best known as a co-founder of the mobile-focused ticketing platform SeatGeek.
E888418 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: Eric Waller | Statement: [SeatGeek, foundedBy, Eric Waller]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Eric Waller
Context triple: [SeatGeek, foundedBy, Eric Waller]
  • A. Michael Wallis
    Michael Wallis is an American historian and author best known for his works on Route 66 and the American West, as well as for voicing the Sheriff in Pixar’s Cars films.
  • B. Ian Wallace
    Ian Wallace is a musician best known as the drummer for the British rock band King Crimson and for his extensive work as a session and touring drummer.
  • C. Ian Wallace
    Ian Wallace is a musician best known as the drummer for the New Zealand rock band The Warriors.
  • D. Robert Walls
    Robert Walls is a former Australian rules football player and premiership-winning coach best known for his coaching stints with several VFL/AFL clubs, including the Brisbane Bears.
  • E. Thomas Wall
    Thomas Wall is a personal name shared by multiple individuals, including historical figures, professionals, and public personalities across various fields.
  • 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: Eric Waller
Triple: [SeatGeek, foundedBy, Eric Waller]
Generated description
Eric Waller is an entrepreneur best known as a co-founder of the mobile-focused ticketing platform SeatGeek.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Eric Waller
Target entity description: Eric Waller is an entrepreneur best known as a co-founder of the mobile-focused ticketing platform SeatGeek.
  • A. Michael Wallis
    Michael Wallis is an American historian and author best known for his works on Route 66 and the American West, as well as for voicing the Sheriff in Pixar’s Cars films.
  • B. Ian Wallace
    Ian Wallace is a musician best known as the drummer for the British rock band King Crimson and for his extensive work as a session and touring drummer.
  • C. Ian Wallace
    Ian Wallace is a musician best known as the drummer for the New Zealand rock band The Warriors.
  • D. Robert Walls
    Robert Walls is a former Australian rules football player and premiership-winning coach best known for his coaching stints with several VFL/AFL clubs, including the Brisbane Bears.
  • E. Thomas Wall
    Thomas Wall is a personal name shared by multiple individuals, including historical figures, professionals, and public personalities across various fields.
  • 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_69d381c733c08190ab1dd6239f5f34ae completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d526d5820c8190a1ad6d6551d093bb completed April 7, 2026, 3:46 p.m.
NED1 Entity disambiguation (via context triple) batch_69deb055648c819085d36458847926b4 completed April 14, 2026, 9:23 p.m.
NEDg Description generation batch_69deb384fb588190ae5d11a60fec0f53 completed April 14, 2026, 9:37 p.m.
NED2 Entity disambiguation (via description) batch_69deb4a2d4c48190a828262b1cc05b37 completed April 14, 2026, 9:41 p.m.
Created at: April 6, 2026, 12:34 p.m.