Triple
T19829354
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John Dutton |
E476414
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Dutton |
—
|
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: Dutton | Statement: [John Dutton, familyName, Dutton]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dutton Context triple: [John Dutton, familyName, Dutton]
-
A.
Dutton
Dutton is the middle name of British Army officer John Dutton Frost, noted for his role in airborne operations during World War II.
-
B.
Dutton
chosen
Dutton is a long-established American book publishing imprint known for releasing a wide range of fiction and nonfiction titles, now operating under Penguin Random House.
-
C.
Dutton
Dutton is a small community located within Elgin County in southwestern Ontario, Canada.
-
D.
Dutton Peabody
Dutton Peabody is the hard-drinking but principled newspaper editor and civic leader in the classic Western film "The Man Who Shot Liberty Valance."
-
E.
Harcout
Harcourt is a small rural town in central Victoria, Australia, known historically for its apple orchards and granite quarries.
- 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_69d8e51c7c188190b926f3a2a7b5f881 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e656ccd3748190adeaed9a431f8979 |
completed | April 20, 2026, 4:39 p.m. |
Created at: April 10, 2026, 1:50 p.m.