Triple
T16437182
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Good to Be Bad |
E399206
|
entity |
| Predicate | featuresMusician |
P20942
|
FINISHED |
| Object | Timothy Drury |
E442734
|
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: Timothy Drury | Statement: [Good to Be Bad, featuresMusician, Timothy Drury]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Timothy Drury Context triple: [Good to Be Bad, featuresMusician, Timothy Drury]
-
A.
Timothy Drury
chosen
Timothy Drury is an American keyboardist, guitarist, and songwriter best known for his work with rock bands such as the Eagles and Whitesnake.
-
B.
Timothy Wolfenden
Timothy Wolfenden is a relative of British journalist and spy Jeremy Wolfenden, belonging to the same notable Wolfenden family.
-
C.
Timothy Cornwell
Timothy Cornwell is a British journalist and writer, known for his work as a foreign correspondent and for being the son of spy novelist John le Carré and editor Valerie Jane Eustace.
-
D.
Jeffrey Stott
Jeffrey Stott is a film producer best known for his work on the political comedy film "The American President."
-
E.
Alec Troup
Alec Troup was a Scottish professional footballer known for playing as a winger in the early 20th century.
- 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_69d87f2c6778819080fcfae53be8f12a |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e32ba49f3481908e7ea62467ef5813 |
completed | April 18, 2026, 6:58 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a01673979608190905afae3071413c0 |
completed | May 11, 2026, 5:20 a.m. |
Created at: April 10, 2026, 5:10 a.m.