Triple
T15020065
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Teacher |
E378059
|
entity |
| Predicate | createdBy |
P806
|
FINISHED |
| Object | Dan Brown |
E72333
|
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: Dan Brown | Statement: [The Teacher, createdBy, Dan Brown]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dan Brown Context triple: [The Teacher, createdBy, Dan Brown]
-
A.
Dan Brown
chosen
Dan Brown is an American author best known for his fast-paced mystery thrillers that blend historical, religious, and conspiracy themes, including the bestselling novel "The Da Vinci Code."
-
B.
Robert Ludlum
Robert Ludlum was an American author best known for his fast-paced espionage and thriller novels, including the Jason Bourne series.
-
C.
Nicholas Evans
Nicholas Evans was a British author best known for his bestselling novel "The Horse Whisperer," which was adapted into a major film.
-
D.
Anthony Horowitz
Anthony Horowitz is a British novelist and screenwriter best known for his Alex Rider spy novels and numerous television crime dramas.
-
E.
Jonathan Harr
Jonathan Harr is an American author and journalist best known for his nonfiction legal thriller "A Civil Action," which chronicles a landmark environmental lawsuit.
- 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_69d85cd3a3c881908c71fc424d459c17 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69ded76445988190984b57de66e00c4a |
completed | April 15, 2026, 12:10 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fe9dd078e481908ec78db57541fc4c |
completed | May 9, 2026, 2:37 a.m. |
Created at: April 10, 2026, 2:56 a.m.