Triple
T21490085
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Back to Back |
E530213
|
entity |
| Predicate | performer |
P1363
|
FINISHED |
| Object | Harry Edison |
—
|
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: Harry Edison | Statement: [Back to Back, performer, Harry Edison]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Harry Edison Context triple: [Back to Back, performer, Harry Edison]
-
A.
Harry Edison
chosen
Harry Edison was an American jazz trumpeter best known for his work with the Count Basie Orchestra and as a prominent studio musician.
-
B.
William Leslie Edison
William Leslie Edison was one of the sons of inventor Thomas Edison, belonging to the Edison family of the famed American inventor.
-
C.
Charles Edison
Charles Edison was an American politician and businessman who served as the 42nd governor of New Jersey and was the son of inventor Thomas Edison and Mina Miller Edison.
-
D.
Edison
"Edison" is a 2005 crime thriller film (also known as "Edison Force") about corruption in a city's elite police unit, featuring an ensemble cast including Morgan Freeman, Kevin Spacey, LL Cool J, and Justin Timberlake.
-
E.
Edison
Edison is a small village in Morrow County, Ohio, United States.
- 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_69e0c45acc3881908e38d3f28964152b |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69e9ea3aee648190ba845f0c7d8110dd |
completed | April 23, 2026, 9:45 a.m. |
Created at: April 16, 2026, 6:22 p.m.