Triple
T18710101
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Greg Iles |
E457483
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Greg Iles |
—
|
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: Greg Iles | Statement: [Greg Iles, name, Greg Iles]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Greg Iles Context triple: [Greg Iles, name, Greg Iles]
-
A.
Greg Iles
chosen
Greg Iles is an American novelist best known for his suspense and crime thrillers, many set in the American South.
-
B.
Douglas Roberts
Douglas Roberts is known primarily as one of the sons of American cable television pioneer and Comcast co-founder Ralph J. Roberts.
-
C.
Nathan Barr
Nathan Barr is an American film and television composer known for his atmospheric scores on projects ranging from horror films to acclaimed series like True Blood and The Americans.
-
D.
Linwood Barclay
Linwood Barclay is a Canadian author best known for his bestselling crime and thriller novels, often featuring ordinary people caught in extraordinary and suspenseful situations.
-
E.
M. Scott Smith
M. Scott Smith is a film editor best known for his work on the crime thriller "To Live and Die in L.A."
- 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_69d8d392aad081909fe31aa03e6e97d1 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e5671a3c8c81909466bf5d81477a37 |
completed | April 19, 2026, 11:36 p.m. |
Created at: April 10, 2026, 11:50 a.m.