Triple
T16185705
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | J. Sterling Morton |
E392793
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Caroline Joy French |
E843722
|
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: Caroline Joy French | Statement: [J. Sterling Morton, spouse, Caroline Joy French]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Caroline Joy French Context triple: [J. Sterling Morton, spouse, Caroline Joy French]
-
A.
Caroline Joy French Morton
chosen
Caroline Joy French Morton was the daughter of American salt magnate and philanthropist Joy Morton, heir to the Morton Salt fortune.
-
B.
Caroline Dhavernas
Caroline Dhavernas is a Canadian actress best known for her roles in television series such as "Wonderfalls" and "Hannibal."
-
C.
Caroline Gordon
Caroline Gordon was an American novelist and critic associated with the Southern Agrarian movement, known for works like "Aleck Maury, Sportsman" and "None Shall Look Back."
-
D.
Caroline Ailin
Caroline Ailin is a Norwegian songwriter and producer known for co-writing major pop hits for artists like Dua Lipa.
-
E.
Caroline Ross
Caroline Ross is a film editor known for her work on the science fiction movie "Starship Troopers."
- 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_69d87f1e49ac8190a311b54d32990576 |
completed | April 10, 2026, 4:39 a.m. |
| NER | Named-entity recognition | batch_69e22060dcf88190b7c662946a5f0191 |
completed | April 17, 2026, 11:58 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a000ecd897c81908cbea306c9f95da3 |
completed | May 10, 2026, 4:51 a.m. |
Created at: April 10, 2026, 5:02 a.m.