Triple
T22250862
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | George Jung |
E549972
|
entity |
| Predicate | hasNickname |
P39
|
FINISHED |
| Object | Boston George |
—
|
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: Boston George | Statement: [George Jung, hasNickname, Boston George]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Boston George Context triple: [George Jung, hasNickname, Boston George]
-
A.
Boston George
chosen
Boston George is the nickname of George Jung, a notorious American drug trafficker who played a major role in the U.S. cocaine trade in the 1970s and 1980s.
-
B.
Boston Commonwealth
Boston Commonwealth was a 19th-century American periodical based in Boston, known for publishing literary and reformist writings.
-
C.
New Boston
New Boston was the original name of the settlement that later became the city of Manhattan, Kansas.
-
D.
Boston T
Boston T is the public rapid transit system serving the Greater Boston area, operated by the Massachusetts Bay Transportation Authority (MBTA).
-
E.
Beantown
Beantown is a popular nickname for the city of Boston, Massachusetts, often used in informal and cultural references to the city.
- 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_69e11e41d9408190bd770cf282e22753 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f138bd45e88190919660d50c0b94bc |
completed | April 28, 2026, 10:46 p.m. |
Created at: April 16, 2026, 8:39 p.m.