Triple
T23181903
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Judy Tyler |
E579483
|
entity |
| Predicate | coStarredWith |
P14987
|
FINISHED |
| Object | Elvis Presley |
—
|
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: Elvis Presley | Statement: [Judy Tyler, coStarredWith, Elvis Presley]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Elvis Presley Context triple: [Judy Tyler, coStarredWith, Elvis Presley]
-
A.
Elvis Presley
chosen
Elvis Presley was an iconic American singer and actor widely known as the "King of Rock and Roll," whose groundbreaking style and charisma transformed popular music and culture in the mid-20th century.
-
B.
Elvis
Elvis is a supporting character in the family adventure film "Free Willy 2: The Adventure Home."
-
C.
Reg Presley
Reg Presley was an English singer-songwriter best known as the lead vocalist of the rock band The Troggs.
-
D.
Vernon Presley
Vernon Presley was the father of rock and roll icon Elvis Presley and served as his son’s business manager and estate executor.
-
E.
Robert Presley
Robert Presley is a cinematographer known for his work on major feature films, including the 2009 adaptation of "A Christmas Carol."
- 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_69e245ff8000819090d12008805315b7 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f18f6f770c81908622085693e37123 |
completed | April 29, 2026, 4:56 a.m. |
Created at: April 17, 2026, 4:05 p.m.