Triple
T22328340
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | William Hayley |
E551959
|
entity |
| Predicate | patronOf |
P2320
|
FINISHED |
| Object | George Romney |
—
|
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: George Romney | Statement: [William Hayley, patronOf, George Romney]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: George Romney Context triple: [William Hayley, patronOf, George Romney]
-
A.
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.
-
B.
W. H. Romney
W. H. Romney was an architect known for designing the Cambridge Theatre in London.
-
C.
John Palmer
John Palmer was the pseudonymous author behind the novel "The House of Dr. Edwardes," later adapted into Alfred Hitchcock’s film "Spellbound."
-
D.
John Palmer
John Palmer is a film industry professional known for his work as an assistant director, including on the movie "Empire."
-
E.
John Palmer
John Palmer was an English architect best known for his work on ecclesiastical buildings in the late 18th and early 19th centuries.
- 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_69e11e482f788190b78d1588fc26d606 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15769fdb48190b84e0c019ab63579 |
completed | April 29, 2026, 12:57 a.m. |
Created at: April 16, 2026, 8:42 p.m.