Triple
T8178750
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Brian May |
E191005
|
entity |
| Predicate | workedWith |
P398
|
FINISHED |
| Object | Roger Taylor |
E512532
|
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: Roger Taylor | Statement: [Brian May, workedWith, Roger Taylor]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Roger Taylor Context triple: [Brian May, workedWith, Roger Taylor]
-
A.
Roger Taylor
chosen
Roger Taylor is an English musician best known as the drummer and a songwriter for the rock band Queen.
-
B.
Charles Watts
Charles Watts was an American character actor known for his supporting roles in mid-20th-century film and television.
-
C.
Keith Relf
Keith Relf was an English musician best known as the lead vocalist and harmonica player for the influential 1960s rock band The Yardbirds.
-
D.
Roger Hodgson
Roger Hodgson is an English musician, singer-songwriter, and co-founder of the progressive rock band Supertramp, known for writing and singing many of their biggest hits.
-
E.
David Parfitt
David Parfitt is a British film producer best known for his Academy Award-winning work on acclaimed dramas such as "Shakespeare in Love."
- 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_69ca82c4538081909404325aa5639483 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb4abd9768819091298e4dd995ac96 |
completed | March 31, 2026, 4:17 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ccbf7f02d08190a6cedc37b64a0d9e |
completed | April 1, 2026, 6:47 a.m. |
Created at: March 30, 2026, 5:40 p.m.