Triple
T20474571
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lester Young |
E502276
|
entity |
| Predicate | alsoKnownAs |
P39
|
FINISHED |
| Object | Prez |
—
|
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: Prez | Statement: [Lester Young, alsoKnownAs, Prez]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Prez Context triple: [Lester Young, alsoKnownAs, Prez]
-
A.
Prez
chosen
Prez is the famous nickname of American jazz tenor saxophonist Lester Young, a pioneering figure in the swing era known for his smooth, lyrical playing style.
-
B.
Prezan
Prezan is a Romanian surname most notably associated with General Constantin Prezan, a key military leader during World War I.
-
C.
Presidentti (President)
Presidentti (President) is the Finnish term for the head of state, most notably the President of the Republic of Finland.
-
D.
Prees
Prees is a village and civil parish in Shropshire, England, with a rural character and a local railway station on the Crewe–Shrewsbury line.
-
E.
The President
The President is the ceremonial head of state of India and the supreme commander of the Indian Armed Forces, elected indirectly to uphold and protect the Constitution.
- 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_69e0b4ae5f1081908768b0c9a3a0bf38 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e699639eec81908f8bd24877b2b876 |
completed | April 20, 2026, 9:23 p.m. |
Created at: April 16, 2026, 11:33 a.m.