Triple
T11721910
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nat Kelly Cole |
E278654
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Nat Kelly Cole |
E278654
|
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: Nat Kelly Cole | Statement: [Nat Kelly Cole, name, Nat Kelly Cole]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Nat Kelly Cole Context triple: [Nat Kelly Cole, name, Nat Kelly Cole]
-
A.
Nat Kelly Cole
chosen
Nat Kelly Cole is one of the daughters of legendary American jazz pianist and singer Nat King Cole.
-
B.
Lenny Cole
Lenny Cole is a ruthless and manipulative London crime boss in the film "RocknRolla," known for orchestrating high-stakes real estate scams and underworld dealings.
-
C.
Red Kelly
Red Kelly was a Canadian Hall of Fame ice hockey defenseman and later politician, renowned for his stellar NHL career with the Detroit Red Wings and Toronto Maple Leafs.
-
D.
Cy Coleman
Cy Coleman was an American composer and songwriter best known for his work on Broadway musicals such as "Sweet Charity," "Barnum," and "City of Angels."
-
E.
Chance Kelly
Chance Kelly is an American actor known for his tough, authoritative roles in film and television, including military and law-enforcement characters.
- 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_69d6aaff2ce88190b4a1e4b341ad5377 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d8a4c373088190bc2ae77a1696d280 |
completed | April 10, 2026, 7:20 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ef83c8ac2c8190b3bba7db42734f3a |
completed | April 27, 2026, 3:42 p.m. |
Created at: April 8, 2026, 9:40 p.m.