Triple
T1714622
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Dark Tower series |
E37261
|
entity |
| Predicate | connectedTo |
P37
|
FINISHED |
| Object | ‘Salem’s Lot |
E37481
|
NE FINISHED |
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: ‘Salem’s Lot | Statement: [The Dark Tower series, connectedTo, ‘Salem’s Lot]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: ‘Salem’s Lot Context triple: [The Dark Tower series, connectedTo, ‘Salem’s Lot]
-
A.
Salem's Lot
chosen
Salem's Lot is a horror novel by Stephen King about a small town slowly overtaken by vampires.
-
B.
Carrie
Carrie is the charming and enigmatic American woman who becomes the central love interest in the British romantic comedy film "Four Weddings and a Funeral."
-
C.
Carrie
"Carrie" is Stephen King's debut horror novel, centered on a bullied teenage girl with telekinetic powers who exacts a devastating revenge on her tormentors.
-
D.
The Fog
The Fog is a 1980 supernatural horror film directed by John Carpenter, centered on a coastal town haunted by vengeful ghosts who return shrouded in an eerie, glowing mist.
-
E.
The Stand
The Stand is a post-apocalyptic horror novel by Stephen King that follows survivors of a devastating plague as they become embroiled in an epic battle between good and evil.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69a8861912dc8190931af43b4b9158a7 |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69aa633349248190822e560fde817fc7 |
completed | March 6, 2026, 5:16 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ad8ae10a048190b7a39e4fb4fbe224 |
completed | March 8, 2026, 2:42 p.m. |
Created at: March 4, 2026, 7:30 p.m.