Triple

T28950
Position Surface form Disambiguated ID Type / Status
Subject Ted Leonsis E577 entity
Predicate familyName P18 FINISHED
Object Leonsis E577 NE FINISHED

How this triple was built (2 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: Leonsis | Statement: [Ted Leonsis, familyName, Leonsis]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Leonsis
Context triple: [Ted Leonsis, familyName, Leonsis]
  • A. Ted Leonsis chosen
    Ted Leonsis is an American businessman, investor, and sports team owner best known for leading Monumental Sports & Entertainment, which owns several major Washington, D.C. professional sports franchises.
  • B. Lionel Hall
    Lionel Hall is an undergraduate dormitory building located within Harvard University's historic Harvard Yard.
  • C. Edwin
    Edwin is a masculine given name of Old English origin meaning "rich friend" or "prosperous friend."
  • D. Harold Hazen
    Harold Hazen was an American electrical engineer and MIT professor known for his pioneering work in control systems and his role in developing early analog computing devices.
  • E. Robert Kraft
    Robert Kraft is an American billionaire businessman and philanthropist best known as the longtime owner of the NFL’s New England Patriots.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69a2479dec388190967ba648663442c9 completed Feb. 28, 2026, 1:40 a.m.
NER Named-entity recognition batch_69a248751fa88190992b6262a44b54f3 completed Feb. 28, 2026, 1:44 a.m.
NED1 Entity disambiguation (via context triple) batch_69a24e5d121c8190bf7bb88346dcc141 completed Feb. 28, 2026, 2:09 a.m.
Created at: Feb. 28, 2026, 1:44 a.m.