Triple
T26880558
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cumberland, Maine |
E676879
|
entity |
| Predicate | CumberlandFairIncludes |
P58216
|
FINISHED |
| Object | harness racing |
—
|
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: harness racing | Statement: [Cumberland, Maine, CumberlandFairIncludes, harness racing]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: CumberlandFairIncludes Context triple: [Cumberland, Maine, CumberlandFairIncludes, harness racing]
-
A.
hasCountyFair
chosen
Indicates that a place or region hosts or holds a county fair event.
-
B.
Apple-ScrappleFestivalFeatures
Indicates that the Apple-Scrapple Festival includes or showcases a particular feature, attraction, or element.
-
C.
worldsFairEdition
Indicates that one entity is a special edition of another that was produced or designated specifically for a World's Fair event.
-
D.
parentFestivalIncludes
Indicates that a larger, parent festival encompasses or contains a smaller, constituent festival as part of its overall program or structure.
-
E.
sharesCeremoniesWith
Indicates that two entities participate in or observe the same ceremonies or ritual practices.
- 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_69eee9bb44988190b6e11652d028bc59 |
completed | April 27, 2026, 4:44 a.m. |
| NER | Named-entity recognition | batch_69f621cbc48881908d104c648c91c715 |
completed | May 2, 2026, 4:09 p.m. |
| PD | Predicate disambiguation | batch_69f620e0b37481909a280574decbd443 |
completed | May 2, 2026, 4:05 p.m. |
Created at: April 27, 2026, 5:39 a.m.