Triple
T8535599
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | George Romney |
E202068
|
entity |
| Predicate | relative |
P37
|
FINISHED |
| Object | Peter Romney |
E202068
|
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: Peter Romney | Statement: [George Romney, relative, Peter Romney]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Peter Romney Context triple: [George Romney, relative, Peter Romney]
-
A.
Jonathan Felton
Jonathan Felton is a sibling of English actor Tom Felton, known for his role as Draco Malfoy in the Harry Potter film series.
-
B.
Jonathan Corwin
Jonathan Corwin was a 17th-century Massachusetts magistrate best known as one of the judges who presided over the Salem witch trials.
-
C.
Brian Rogers
Brian Rogers is a film producer best known for his work on the 2014 reboot of the Godzilla franchise.
-
D.
George Romney
chosen
George Romney was an 18th-century English portrait painter renowned for his elegant depictions of British high society, including notable figures such as Emma Hamilton.
-
E.
Lamont Bentley
Lamont Bentley was an American actor best known for his role as Hakeem Campbell on the 1990s television sitcom "Moesha."
- 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_69ca832355b08190b8b6a4ab4a4a3554 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbe6a295c88190a432a060ee73f04e |
completed | March 31, 2026, 3:22 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ce890eb0b48190aa76cc955d00ec18 |
completed | April 2, 2026, 3:19 p.m. |
Created at: March 30, 2026, 6:17 p.m.