Triple
T34449961
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cambridge Raceway |
E884335
|
entity |
| Predicate | hasRacetrackSurface |
P115885
|
FINISHED |
| Object | all-weather surface |
—
|
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: all-weather surface | Statement: [Cambridge Raceway, hasRacetrackSurface, all-weather surface]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasRacetrackSurface Context triple: [Cambridge Raceway, hasRacetrackSurface, all-weather surface]
-
A.
hasRaceSurface
Indicates that an event or activity takes place on, or is associated with, a specific type of race surface.
-
B.
hasRacingSurfacePreference
Indicates that an entity has a favored or typical type of racing surface on which it prefers to compete or perform.
-
C.
hasTrackSurface
chosen
Indicates that an entity (such as a track) possesses or is characterized by a particular type of surface.
-
D.
hasRacingSide
Indicates that an entity possesses or is associated with a side or aspect specifically dedicated to racing.
-
E.
hasRailTrailSurface
Indicates that a rail trail possesses a specific type of surface material or finish.
- 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_69f349c607688190b553539d14901a35 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69fd35d108908190b79b1e8e6bbd62aa |
completed | May 8, 2026, 1:01 a.m. |
| PD | Predicate disambiguation | batch_69fd34cb46108190b43c3b7f67ec4cd4 |
completed | May 8, 2026, 12:56 a.m. |
Created at: May 1, 2026, 2 a.m.