Triple
T27464287
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mulsanne Straight |
E693133
|
entity |
| Predicate | maximumSpeedsReachedBeforeChicanes |
P12248
|
FINISHED |
| Object | over 400 km/h |
—
|
LITERAL 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: over 400 km/h | Statement: [Mulsanne Straight, maximumSpeedsReachedBeforeChicanes, over 400 km/h]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: maximumSpeedsReachedBeforeChicanes Context triple: [Mulsanne Straight, maximumSpeedsReachedBeforeChicanes, over 400 km/h]
-
A.
hasChicane
Indicates that one entity incorporates or features a chicane (a sharp, S-shaped bend or series of bends), typically in the context of a track, route, or path.
-
B.
speedAchieved
chosen
Indicates that a particular speed has been reached or attained by an entity during an event or action.
-
C.
fastestLapTime
Indicates the shortest recorded time an entity achieved to complete a single lap in a given context or event.
-
D.
maximumSpeedRecord
Indicates that an entity holds the highest recorded speed value (a speed record) within a given context or category.
-
E.
safetyCarLapRecordHolder
Indicates that one entity holds the record for the most notable or fastest performance during a lap completed under safety car conditions in a race.
- F. None of above.
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_69ef538105548190a771cc5a0cf8c211 |
completed | April 27, 2026, 12:16 p.m. |
| NER | Named-entity recognition | batch_69f68f670b608190a0b6ab60d722b4e0 |
completed | May 2, 2026, 11:57 p.m. |
| PD | Predicate disambiguation | batch_69f68b78f29481908cc8f390496dee97 |
completed | May 2, 2026, 11:40 p.m. |
Created at: April 27, 2026, 12:51 p.m.