Triple
T804607
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Boss |
E17400
|
entity |
| Predicate | teamName |
P7598
|
FINISHED |
| Object | Tartan Racing |
E95170
|
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: Tartan Racing | Statement: [Boss, teamName, Tartan Racing]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tartan Racing Context triple: [Boss, teamName, Tartan Racing]
-
A.
Tartan Racing
chosen
Tartan Racing is an autonomous vehicle research team formed by Carnegie Mellon University and General Motors that gained prominence by winning the 2007 DARPA Urban Challenge.
-
B.
Midland F1 Racing
Midland F1 Racing was a short-lived Formula One team that competed in the mid-2000s under Russian ownership before being sold and rebranded.
-
C.
RCS Sport
RCS Sport is an Italian sports and media company best known for organizing major cycling races and other sporting events.
-
D.
St Rollox Works
St Rollox Works was a major railway engineering and locomotive repair facility in Glasgow, Scotland, historically significant for its role in maintaining and constructing rolling stock for British railways.
-
E.
Gazoo Racing
Gazoo Racing is Toyota’s global motorsport and high-performance division, responsible for its racing activities and sporty road car models.
- 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_69a4937ae8a08190b5084a03d532b30e |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a4aabebff08190880e4876ff58bcfe |
completed | March 1, 2026, 9:08 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a76d83cf448190a2205cd777386833 |
completed | March 3, 2026, 11:23 p.m. |
Created at: March 1, 2026, 7:38 p.m.