Triple
T7219903
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sir Visto |
E150229
|
entity |
| Predicate | trainer |
P41095
|
FINISHED |
| Object | Mathew Dawson |
E649689
|
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: Mathew Dawson | Statement: [Sir Visto, trainer, Mathew Dawson]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mathew Dawson Context triple: [Sir Visto, trainer, Mathew Dawson]
-
A.
Matthew Dawson
chosen
Matthew Dawson was a prominent 19th-century British racehorse trainer renowned for preparing multiple classic-winning Thoroughbreds.
-
B.
Mathew Prichard
Mathew Prichard is a British television producer and the grandson of famed mystery writer Agatha Christie, known for overseeing adaptations of her works.
-
C.
Alex Mather
Alex Mather is an American entrepreneur best known as the co-founder of the sports media company The Athletic.
-
D.
Adam Gough
Adam Gough is a British film editor known for his work on acclaimed films such as "Da 5 Bloods" and "Roma."
-
E.
Andrew Robinson
Andrew Robinson is an American actor best known for his roles in films like "Dirty Harry" and the TV series "Star Trek: Deep Space Nine."
- 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_69c687effb44819092b95d07d0368c9f |
completed | March 27, 2026, 1:36 p.m. |
| NER | Named-entity recognition | batch_69c6e9b1a7908190bd215ffb84592e32 |
completed | March 27, 2026, 8:33 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c7d38423bc8190aaf4ee3940813d33 |
completed | March 28, 2026, 1:11 p.m. |
Created at: March 27, 2026, 2:53 p.m.