Triple
T22127107
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Four |
E546816
|
entity |
| Predicate | producer |
P490
|
FINISHED |
| Object | Ed Drewett |
—
|
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: Ed Drewett | Statement: [Four, producer, Ed Drewett]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ed Drewett Context triple: [Four, producer, Ed Drewett]
-
A.
Ed Drewett
chosen
Ed Drewett is a British singer-songwriter best known for co-writing major pop hits for artists such as One Direction, Little Mix, and The Wanted.
-
B.
Martin Drewes
Martin Drewes was a highly successful German Luftwaffe night fighter ace of World War II, credited with numerous aerial victories during nocturnal operations.
-
C.
Douglas Brunt
Douglas Brunt is an American novelist and former CEO of the cybersecurity firm Authentium, known also as the husband of journalist Megyn Kelly.
-
D.
Ben Drew
Ben Drew is an English rapper, singer-songwriter, actor, and filmmaker best known by his stage name Plan B.
-
E.
Chris Blunden
Chris Blunden is a film editor known for his work on the 1997 comedy film "Bean."
- 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_69e11e39bf348190b541bfa16a7b71e0 |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f12982eaa08190933d3036c020f562 |
completed | April 28, 2026, 9:41 p.m. |
Created at: April 16, 2026, 8:31 p.m.