Triple
T11667862
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Room Full of Roses |
E277300
|
entity |
| Predicate | recordedBy |
P1165
|
FINISHED |
| Object | George Morgan |
E939383
|
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: George Morgan | Statement: [Room Full of Roses, recordedBy, George Morgan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: George Morgan Context triple: [Room Full of Roses, recordedBy, George Morgan]
-
A.
George Morgan
chosen
George Morgan was an American country music singer best known for his smooth vocal style and mid-20th-century hits.
-
B.
George Virginia Morgan
George Virginia Morgan is the daughter of American actress Hilarie Burton and actor Jeffrey Dean Morgan.
-
C.
George T. Morgan
George T. Morgan was a British-born American engraver best known as the U.S. Mint designer of the iconic Morgan silver dollar.
-
D.
George Arthur
George Arthur was a 19th-century British colonial administrator best known for his conservative and often controversial governance in British North America and Australia.
-
E.
Joseph Curwen
Joseph Curwen is a sinister 18th-century sorcerer and necromancer whose dark legacy drives the occult horrors in H. P. Lovecraft’s novel "The Case of Charles Dexter Ward."
- 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_69d6aafd0a448190b44da30af8c6c519 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d8a440d8a481909a13c97813408bc8 |
completed | April 10, 2026, 7:18 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ef82e252fc819082b5c8a33fcf861a |
completed | April 27, 2026, 3:38 p.m. |
Created at: April 8, 2026, 9:39 p.m.