Triple
T19897875
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mercury and Me |
E478198
|
entity |
| Predicate | author |
P4
|
FINISHED |
| Object | Jim Hutton |
—
|
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: Jim Hutton | Statement: [Mercury and Me, author, Jim Hutton]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jim Hutton Context triple: [Mercury and Me, author, Jim Hutton]
-
A.
Jim Hutton
chosen
Jim Hutton was an Irish hairdresser best known as the long-term partner of Queen frontman Freddie Mercury during the final years of Mercury’s life.
-
B.
Jim Hutton
Jim Hutton was an American actor best known for his lanky, affable screen presence in 1960s comedies and for playing the title role in the TV series "Ellery Queen."
-
C.
Jim Hensley
Jim Hensley was an American businessman and beer distributor best known as the founder of Hensley & Co., one of the largest Anheuser-Busch distributors in the United States.
-
D.
Steve Hulett
Steve Hulett is an American screenwriter best known for his work at Disney, including contributing to the animated film "The Great Mouse Detective."
-
E.
Brad Hunstable
Brad Hunstable is an American entrepreneur best known as the co-founder and former CEO of the live video streaming platform Ustream.
- 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_69d8e520682081909892916424699bd5 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e6593ef8dc8190be5b64988eceafac |
completed | April 20, 2026, 4:50 p.m. |
Created at: April 10, 2026, 1:52 p.m.