Triple
T20478451
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Eliza Bennett |
E502384
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Sweet/Vicious |
—
|
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: Sweet/Vicious | Statement: [Eliza Bennett, notableWork, Sweet/Vicious]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sweet/Vicious Context triple: [Eliza Bennett, notableWork, Sweet/Vicious]
-
A.
Sweet/Vicious
chosen
Sweet/Vicious is a darkly comedic TV drama about two college women who secretly become vigilantes targeting sexual predators on their campus.
-
B.
Vicious
Vicious is a British sitcom starring Derek Jacobi and Ian McKellen as a long-term gay couple navigating their acerbic yet affectionate relationship in London.
-
C.
Vicious
Vicious is a novel that follows Ash Weston, a morally complex protagonist navigating a dark, superpowered world of revenge and ambition.
-
D.
Vicious
Vicious is a ruthless and power-hungry crime lord in the live-action Cowboy Bebop series, serving as Spike Spiegel’s primary nemesis.
-
E.
Vicious
Vicious is a hip-hop artist known for collaborating with The Hip-Hop Violinist on genre-blending tracks.
- 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_69e0b4af32848190aea80682b44d5d6e |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e69b54c8188190a71e35fab8d194a6 |
completed | April 20, 2026, 9:32 p.m. |
Created at: April 16, 2026, 11:34 a.m.