Triple
T37680600
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Flowery Branch |
E938218
|
entity |
| Predicate | hasSportsFacilityRole |
P198778
|
FINISHED |
| Object | Atlanta Falcons training camp site |
—
|
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: Atlanta Falcons training camp site | Statement: [Flowery Branch, hasSportsFacilityRole, Atlanta Falcons training camp site]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSportsFacilityRole Context triple: [Flowery Branch, hasSportsFacilityRole, Atlanta Falcons training camp site]
-
A.
sportsFacility
Indicates that one entity is a sports facility where sports or physical activities can take place for the other entity.
-
B.
isSportsFacilityOfCountry
Indicates that a sports facility is located in, belongs to, or is officially associated with a specified country.
-
C.
isPartOfSportsVenue
Indicates that one entity is a component, section, or area contained within a larger sports venue.
-
D.
hasSportsVenueType
Indicates that a sports venue is classified as being of a specific type or category (e.g., stadium, arena, court).
-
E.
hasProfessionalSportsVenue
Indicates that one entity possesses or hosts a venue specifically used for professional sports events.
- 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_69f76ed881408190bc62a969530a4a53 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69ff0491409c8190be40f633a58da0b1 |
completed | May 9, 2026, 9:55 a.m. |
| PD | Predicate disambiguation | batch_69ff040bb5cc81909534c7eee85d5e90 |
completed | May 9, 2026, 9:53 a.m. |
| PDg | Predicate description generation | batch_69ff04901ab081908b68563836fcdc99 |
completed | May 9, 2026, 9:55 a.m. |
Created at: May 3, 2026, 4:18 p.m.