Triple
T9089005
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Repton School |
E217829
|
entity |
| Predicate | notableAlumnus |
P304
|
FINISHED |
| Object | Jeremy Clarkson |
E632661
|
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: Jeremy Clarkson | Statement: [Repton School, notableAlumnus, Jeremy Clarkson]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jeremy Clarkson Context triple: [Repton School, notableAlumnus, Jeremy Clarkson]
-
A.
Jeremy Clarkson
chosen
Jeremy Clarkson is a British television presenter, journalist, and writer best known for co-hosting the motoring shows Top Gear and The Grand Tour.
-
B.
James May
James May is a British television presenter, journalist, and writer best known as a former co-host of the motoring show "Top Gear" and later "The Grand Tour."
-
C.
Martin Brundle
Martin Brundle is a former British Formula One driver who became widely known as a leading F1 television commentator and analyst.
-
D.
Jim May
Jim May is a film editor best known for his work on major action movies, including the 2010 adaptation of "The A-Team."
-
E.
Murray Walker
Murray Walker was a renowned British motorsport commentator best known for his excitable, fast-paced Formula One commentary and distinctive voice.
- 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_69ca83d8ab5881909d8fddae363b32b1 |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cc9657d48081909e0ae0f1fa8ff599 |
completed | April 1, 2026, 3:51 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d017e0d3cc8190b3e92b0a8f18489f |
completed | April 3, 2026, 7:41 p.m. |
Created at: March 30, 2026, 7:14 p.m.