Triple
T6106239
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Charles Boyle |
E136123
|
entity |
| Predicate | closeFriend |
P8712
|
FINISHED |
| Object | Terry Jeffords |
E180127
|
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: Terry Jeffords | Statement: [Charles Boyle, closeFriend, Terry Jeffords]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Terry Jeffords Context triple: [Charles Boyle, closeFriend, Terry Jeffords]
-
A.
Terry Jeffords
chosen
Terry Jeffords is a devoted family man and physically imposing yet gentle sergeant in the comedy series "Brooklyn Nine-Nine," known for his leadership, sensitivity, and love of yogurt.
-
B.
Tim Latta
Tim Latta is a soccer executive best known for serving as the general manager of the early Major League Soccer club Kansas City Wiz (now Sporting Kansas City).
-
C.
Randy Bricker
Randy Bricker is a film editor known for his work on horror and genre films, including Texas Chainsaw 3D.
-
D.
Ted Cheesman
Ted Cheesman was a film editor best known for his work on classic Hollywood productions, including the 1933 monster film "King Kong."
-
E.
Dennis Dugan
Dennis Dugan is an American film director, actor, and comedian best known for directing numerous Adam Sandler-led comedies such as "Happy Gilmore," "Big Daddy," and "Grown Ups."
- 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_69c0087dee9881909e3655be88208c01 |
completed | March 22, 2026, 3:19 p.m. |
| NER | Named-entity recognition | batch_69c05b806bd48190b6f020af3391adb8 |
completed | March 22, 2026, 9:13 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c62cfca10c8190b9e0691ba90fff02 |
completed | March 27, 2026, 7:08 a.m. |
Created at: March 22, 2026, 4:13 p.m.