Triple
T17961652
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dr. Kananga |
E449097
|
entity |
| Predicate | alias |
P39
|
FINISHED |
| Object | Mr. Big |
—
|
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: Mr. Big | Statement: [Dr. Kananga, alias, Mr. Big]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mr. Big Context triple: [Dr. Kananga, alias, Mr. Big]
-
A.
Mr. Big
chosen
Mr. Big is the primary villain and drug lord antagonist in the James Bond film and novel "Live and Let Die."
-
B.
Mr. Big
Mr. Big is the charismatic, commitment-phobic love interest of Carrie Bradshaw in the Sex and the City franchise.
-
C.
Mr. Big
Mr. Big is a powerful arctic shrew crime boss in Disney's animated film "Zootopia," known for his mafia-style persona and eventual alliance with protagonist Nick Wilde.
-
D.
Mr. Big Stuff
"Mr. Big Stuff" is a popular hip-hop track by Heavy D & the Boyz known for its upbeat groove and charismatic, playful lyrics.
-
E.
Loverboy
Loverboy is a Canadian rock band best known for its 1980s hits like "Working for the Weekend" and its energetic, radio-friendly arena rock sound.
- 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.