Triple
T17961675
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dr. Kananga |
E449097
|
entity |
| Predicate | employs |
P7
|
FINISHED |
| Object | Baron Samedi |
—
|
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: Baron Samedi | Statement: [Dr. Kananga, employs, Baron Samedi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Baron Samedi Context triple: [Dr. Kananga, employs, Baron Samedi]
-
A.
Baron Samedi
chosen
Baron Samedi is a prominent Haitian Vodou spirit of death, the cemetery, and the crossroads between the living and the dead, often depicted in a top hat, dark glasses, and formal attire.
-
B.
Trompe-la-Mort
Trompe-la-Mort is the underworld alias of Vautrin, a cunning and enigmatic criminal mastermind in Honoré de Balzac’s La Comédie humaine.
-
C.
Manuel Sanguily
Manuel Sanguily was a prominent Cuban lawyer, politician, and revolutionary leader known for his role in Cuba’s struggle for independence from Spain.
-
D.
Ghoul
Ghoul is a horror film featuring Nolan Gould in its cast.
-
E.
Vodoo
Vodoo is the gaming alias of Alexander "Vodoo" Beutel, a professional esports player and streamer known in the competitive gaming community.
- 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.