Triple
T36147338
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | FEI Driving |
E1045486
|
entity |
| Predicate | hasMarathonComponent |
P204088
|
FINISHED |
| Object | cross-country course with obstacles |
—
|
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: cross-country course with obstacles | Statement: [FEI Driving, hasMarathonComponent, cross-country course with obstacles]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasMarathonComponent Context triple: [FEI Driving, hasMarathonComponent, cross-country course with obstacles]
-
A.
marathonAchievement
Indicates that an entity has successfully completed or achieved a significant result in a marathon event.
-
B.
hasSprintRace
Indicates that an event or competition includes a sprint-format race as part of its structure or schedule.
-
C.
hasThroughRunning
Indicates that there is a continuous, through-running service or operation connecting two points without requiring a transfer or interruption.
-
D.
hasSprintRaceInSomeYears
Indicates that the associated entity has held or will hold a sprint race in at least one, but not necessarily all, of the years in question.
-
E.
hasOutrun
Indicates that one entity has run faster than and moved ahead of another entity in a race or chase.
- F. None of above. chosen
Provenance (4 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_69f76e37ace88190a906b107d388f5d1 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_6a031e24299c81908dcbbf1b88f43dfd |
completed | May 12, 2026, 12:33 p.m. |
| PD | Predicate disambiguation | batch_6a031ce232a48190b62bca3e94162f2f |
completed | May 12, 2026, 12:28 p.m. |
| PDg | Predicate description generation | batch_6a031e231290819086c8869c8039f1f8 |
completed | May 12, 2026, 12:33 p.m. |
Created at: May 3, 2026, 4:08 p.m.