Triple
T6966274
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | George Jefferson |
E161495
|
entity |
| Predicate | neighbor |
P350
|
FINISHED |
| Object | Harry Bentley |
E164741
|
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: Harry Bentley | Statement: [George Jefferson, neighbor, Harry Bentley]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Harry Bentley Context triple: [George Jefferson, neighbor, Harry Bentley]
-
A.
Harry Bentley
chosen
Harry Bentley is a quirky, soft-spoken British neighbor and United Nations translator on the classic American sitcom "The Jeffersons."
-
B.
Henry Snodgrass
Henry Snodgrass was an American Major League Baseball outfielder who played in the early 20th century, best remembered for his time with the New York Giants.
-
C.
Howard Bannister
Howard Bannister is the mild-mannered, musicologist protagonist played by Ryan O'Neal in the screwball comedy film "What's Up, Doc?".
-
D.
Charles Butterworth
Charles Butterworth was an American comic film actor of the 1930s and early 1940s, known for his dry, dithering persona in numerous Hollywood comedies.
-
E.
Henry Buckley
Henry Buckley is a personal name shared by several notable individuals, including politicians, journalists, and public figures.
- 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_69c68853cff881908439d488924a8283 |
completed | March 27, 2026, 1:38 p.m. |
| NER | Named-entity recognition | batch_69c6db121174819098e73e45f6c9cc91 |
completed | March 27, 2026, 7:31 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c758a57b8481908cef7de9b3abf7a3 |
completed | March 28, 2026, 4:27 a.m. |
Created at: March 27, 2026, 2:30 p.m.