Triple
T17870806
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John Hunter |
E446829
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | John Hunter |
—
|
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: John Hunter | Statement: [John Hunter, name, John Hunter]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: John Hunter Context triple: [John Hunter, name, John Hunter]
-
A.
John Hunter
John Hunter was a prominent landowner and early settler after whom the Town of Hunter in New York was named.
-
B.
John Hunter
John Hunter was an influential 18th-century Scottish surgeon and anatomist, often regarded as a founder of modern scientific surgery.
-
C.
John Hunter
John Hunter was a British Royal Navy officer who later became the second Governor of New South Wales in Australia.
-
D.
John Gillon
John Gillon is the central protagonist of the film "Diggstown," a cunning ex-con and boxing hustler who masterminds an elaborate scheme around a small-town boxing challenge.
-
E.
William Hunter
William Hunter was an 18th-century printer and publisher known for issuing influential Masonic works, including Anderson’s Constitutions of 1723.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide. chosen
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_69d8b9f4c22c819093c2680434472894 |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e49aa24c8481909de38953a88ff615 |
completed | April 19, 2026, 9:04 a.m. |
Created at: April 10, 2026, 10:18 a.m.