Triple
T17961674
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dr. Kananga |
E449097
|
entity |
| Predicate | employs |
P7
|
FINISHED |
| Object | Tee Hee Johnson |
—
|
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: Tee Hee Johnson | Statement: [Dr. Kananga, employs, Tee Hee Johnson]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tee Hee Johnson Context triple: [Dr. Kananga, employs, Tee Hee Johnson]
-
A.
Tee Hee Johnson
chosen
Tee Hee Johnson is a henchman with a mechanical arm who serves as one of the main villains’ enforcers in the James Bond film "Live and Let Die."
-
B.
Dee Johnson
Dee Johnson is an American television writer and producer known for her work on series such as ER, Nashville, and The Good Wife.
-
C.
Dee Johnson
Dee Johnson is known as the wife of American politician and former New Mexico governor Gary Johnson.
-
D.
Enotris Johnson
Enotris Johnson was a songwriter best known for co-writing the rock and roll classic "Long Tall Sally," popularized by Little Richard.
-
E.
Libet Johnson
Libet Johnson is a member of the Johnson family associated with the Johnson & Johnson business dynasty and its pharmaceutical and consumer goods fortune.
- 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_69d8b9f8cca8819099836916c56b7c95 |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e4b132cc10819088526a0b4b098d69 |
completed | April 19, 2026, 10:40 a.m. |
Created at: April 10, 2026, 10:22 a.m.