Triple
T10297844
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marlborough College |
E241542
|
entity |
| Predicate | hasNotableAlumni |
P51
|
FINISHED |
| Object | Mark Phillips |
E107494
|
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: Mark Phillips | Statement: [Marlborough College, hasNotableAlumni, Mark Phillips]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mark Phillips Context triple: [Marlborough College, hasNotableAlumni, Mark Phillips]
-
A.
Mark Phillips
chosen
Mark Phillips is a British former Olympic equestrian and army officer best known for his marriage to Anne, Princess Royal.
-
B.
Graham Massey
Graham Massey is a British musician, producer, and composer best known as a founding member of the influential electronic music group 808 State.
-
C.
Tom Pocock
Tom Pocock was a British biographer, historian, and journalist best known for his works on naval history and figures from the Napoleonic era.
-
D.
Colin Jones
Colin Jones is a fictional character in the Bridget Jones series, known primarily as Bridget Jones’s father.
-
E.
Colin Jones
Colin Jones is a film producer known for his work on the acclaimed documentary "Ai Weiwei: Never Sorry."
- 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_69d381aaafc08190af475ef58dc16aba |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4d2ed50908190962f0d6d049fb964 |
completed | April 7, 2026, 9:48 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d71d2cc9c48190bc36f6a4f8144b7f |
completed | April 9, 2026, 3:29 a.m. |
Created at: April 6, 2026, 11:43 a.m.