Triple
T23187238
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Great American River Run |
E579624
|
entity |
| Predicate | hasDistanceEvent |
P27047
|
FINISHED |
| Object | half marathon |
—
|
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: half marathon | Statement: [Great American River Run, hasDistanceEvent, half marathon]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasDistanceEvent Context triple: [Great American River Run, hasDistanceEvent, half marathon]
-
A.
hasDistanceCategory
Indicates that one entity is associated with a qualitative or categorical classification of its distance relative to another entity or reference point.
-
B.
raceDistanceType
chosen
Indicates the specific type or category of distance over which a race is conducted.
-
C.
isRelayRace
Indicates that the activity or event is a relay race, where multiple participants or teams take turns completing segments of a race in sequence.
-
D.
distancePerRace
Indicates the total distance covered in a single race event or instance.
-
E.
majorRaceDistance
Indicates the standard or primary distance over which a major race or competition is contested.
- 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_69e245ff8000819090d12008805315b7 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f18fd4c6f481908b6138a44b98c8a7 |
completed | April 29, 2026, 4:57 a.m. |
| PD | Predicate disambiguation | batch_69ef8a041c0081909afb670d17a5aaba |
completed | April 27, 2026, 4:08 p.m. |
Created at: April 17, 2026, 4:05 p.m.