Triple
T18056412
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hannibal Rising |
E432049
|
entity |
| Predicate | screenwriter |
P2831
|
FINISHED |
| Object | Thomas Harris |
—
|
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: Thomas Harris | Statement: [Hannibal Rising, screenwriter, Thomas Harris]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Thomas Harris Context triple: [Hannibal Rising, screenwriter, Thomas Harris]
-
A.
Thomas Harris
chosen
Thomas Harris is an American novelist best known for creating the character Hannibal Lecter in his series of psychological horror thrillers.
-
B.
Thomas B. Harris
Thomas B. Harris was a local figure of historical significance after whom the village of Thomasboro, Illinois, was named.
-
C.
Jeff Lindsay
Jeff Lindsay is an American novelist best known for creating the character Dexter Morgan in the crime thriller series that inspired the television show "Dexter."
-
D.
Jeffery Deaver
Jeffery Deaver is an American mystery and thriller author best known for his Lincoln Rhyme series and for writing a James Bond novel, "Carte Blanche."
-
E.
Patricia Cornwell
Patricia Cornwell is an American crime writer best known for her bestselling Kay Scarpetta series of forensic thrillers.
- 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_69d8b906482481908183315b9ecf9994 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4c102d08081908d2419c898213400 |
completed | April 19, 2026, 11:48 a.m. |
Created at: April 10, 2026, 10:26 a.m.