Triple
T18335860
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lee Haney |
E439267
|
entity |
| Predicate | founded |
P104
|
FINISHED |
| Object | Lee Haney Games |
—
|
NE NERFINISHED |
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: Lee Haney Games | Statement: [Lee Haney, founded, Lee Haney Games]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lee Haney Games Context triple: [Lee Haney, founded, Lee Haney Games]
-
A.
Lee Haney
chosen
Lee Haney is an American professional bodybuilder best known for winning a record eight Mr. Olympia titles, tying him with Ronnie Coleman for the most in history.
-
B.
Gary Haney
Gary Haney is an American architect best known for his work with Skidmore, Owings & Merrill on major international skyscraper projects.
-
C.
CB Hudson
CB Hudson is an American guitarist best known for his work with the rock band Blue October.
-
D.
Ted McCord
Ted McCord was an American cinematographer known for his work on numerous classic Hollywood films, including the Oscar-nominated Johnny Belinda and The Sound of Music.
-
E.
John Chaney
John Chaney was a Hall of Fame American college basketball coach best known for transforming Temple University into a national powerhouse with his tough, defense-first teams.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8b9175fec8190af865699b4e64d8c |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e50ecd759481909703ed2d0d68199f |
completed | April 19, 2026, 5:20 p.m. |
Created at: April 10, 2026, 10:37 a.m.