Triple
T17878157
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sophie Ellis-Bextor |
E447010
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Richard Jones |
—
|
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: Richard Jones | Statement: [Sophie Ellis-Bextor, spouse, Richard Jones]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Richard Jones Context triple: [Sophie Ellis-Bextor, spouse, Richard Jones]
-
A.
Richard Jones
Richard Jones was a 16th-century London printer and publisher known for issuing early editions of important Elizabethan works, including Christopher Marlowe’s "Tamburlaine."
-
B.
Richard Jones
Richard Jones was an English Baroque composer and violinist active in the early 18th century, known for his theatrical and instrumental music.
-
C.
Richard Jones
chosen
Richard Jones is the longtime bassist for the Welsh rock band Stereophonics.
-
D.
Richard Jones
Richard Jones is a Python software developer and community contributor known for his work on Python packaging standards and tools.
-
E.
Stan Jones
Stan Jones was an American songwriter and actor best known for writing the classic Western song "Ghost Riders in the Sky."
- 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_69d8b9f4c22c819093c2680434472894 |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e49c0c46108190b8edef2572b5ba90 |
completed | April 19, 2026, 9:10 a.m. |
Created at: April 10, 2026, 10:18 a.m.