Triple
T23340513
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Susan Gordon |
E591721
|
entity |
| Predicate | performedIn |
P795
|
FINISHED |
| Object | Tormented |
—
|
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: Tormented | Statement: [Susan Gordon, performedIn, Tormented]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tormented Context triple: [Susan Gordon, performedIn, Tormented]
-
A.
Tormented
chosen
Tormented is a 1960 American horror film about a man haunted by the vengeful ghost of his former lover after her death under suspicious circumstances.
-
B.
Tormented
Tormented is the 1996 debut studio album by American rock band Staind, showcasing their early heavy, raw nu-metal sound.
-
C.
Tormentor
Tormentor is a song by the American thrash metal band Slayer, featured on their debut album "Show No Mercy."
-
D.
Infernal
"Infernal" is a horror-thriller novel by F. Paul Wilson, part of his Repairman Jack series that blends supernatural elements with suspense and dark adventure.
-
E.
The Suffering
The Suffering is a horror-themed action video game known for its brutal combat, psychological elements, and morally driven narrative set within a haunted prison.
- 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_69e25d20e3d08190bcede87673cafb25 |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f198329d9c8190992627afa9b54bed |
completed | April 29, 2026, 5:33 a.m. |
Created at: April 17, 2026, 5:18 p.m.