Triple
T5884658
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Buffalo Bill |
E130830
|
entity |
| Predicate | associatedWith |
P37
|
FINISHED |
| Object | Hannibal Lecter |
E130828
|
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: Hannibal Lecter | Statement: [Buffalo Bill, associatedWith, Hannibal Lecter]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hannibal Lecter Context triple: [Buffalo Bill, associatedWith, Hannibal Lecter]
-
A.
Hannibal Lecter
chosen
Hannibal Lecter is a brilliant but psychopathic cannibalistic serial killer and psychiatrist, best known as the chilling antagonist in Thomas Harris’s novels and their film adaptations.
-
B.
Francis Dolarhyde
Francis Dolarhyde is the fictional serial killer known as "The Tooth Fairy" in Thomas Harris's novel *Red Dragon* and its screen adaptations.
-
C.
Michael Ripps
Michael Ripps is a film editor known for his work on the movie "Stakeout."
-
D.
Tom Ripley
Tom Ripley is a charming yet deeply amoral con artist and serial imposter best known as the psychologically complex antihero of Patricia Highsmith’s crime novels.
-
E.
Thomas Ripley
Thomas Ripley was an 18th-century English architect and master carpenter known for his work on prominent country houses and public buildings, including contributions to Palladian architecture.
- 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_69c0085628dc8190b334c1b44c067efc |
completed | March 22, 2026, 3:18 p.m. |
| NER | Named-entity recognition | batch_69c0367743508190bae211e9ce8f9690 |
completed | March 22, 2026, 6:35 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c108039acc8190a5ce23412f1a359c |
completed | March 23, 2026, 9:29 a.m. |
Created at: March 22, 2026, 3:57 p.m.