Triple
T16529948
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thrust2 |
E401536
|
entity |
| Predicate | crewRole |
P2094
|
FINISHED |
| Object | driver Richard Noble |
E1218187
|
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: driver Richard Noble | Statement: [Thrust2, crewRole, driver Richard Noble]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: driver Richard Noble Context triple: [Thrust2, crewRole, driver Richard Noble]
-
A.
Richard Noble
chosen
Richard Noble is a British entrepreneur and former land speed record holder best known for leading high-speed car projects such as Thrust2.
-
B.
Donald Campbell
Donald Campbell was a British speed record breaker famed for his attempts on both land and water, ultimately losing his life during a water speed record attempt on Coniston Water in 1967.
-
C.
Ken Miles
Ken Miles was a British-born racing driver and engineer best known for his pivotal role in Ford’s 1960s Le Mans program and his portrayal in the film "Ford v Ferrari."
-
D.
Jim May
Jim May is an editor known for his work on the role-playing game publication "Pathfinder."
-
E.
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."
- 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_69d883838abc8190bc79cb2d41733ce2 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e32ed625208190a68b879266b05b3f |
completed | April 18, 2026, 7:12 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a006ed808448190936ea51a9a28a95a |
completed | May 10, 2026, 11:41 a.m. |
Created at: April 10, 2026, 5:14 a.m.