Triple
T37680613
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Flowery Branch |
E938218
|
entity |
| Predicate | hasSportsTeamFacility |
P2500
|
FINISHED |
| Object | Atlanta Falcons headquarters and training complex |
—
|
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 headquarters and training complex | Statement: [Flowery Branch, hasSportsTeamFacility, Atlanta Falcons headquarters and training complex]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSportsTeamFacility Context triple: [Flowery Branch, hasSportsTeamFacility, Atlanta Falcons headquarters and training complex]
-
A.
hasSportsTeamVenueFor
Indicates that a venue serves as the home or hosting location for a particular sports team.
-
B.
hasSportsFacilityRole
Indicates that an entity holds a specific role, function, or position associated with a sports facility.
-
C.
hasProfessionalSportsVenue
Indicates that one entity possesses or hosts a venue specifically used for professional sports events.
-
D.
hasSportsTeam
Indicates that an entity possesses, sponsors, or is represented by a sports team.
-
E.
sportsFacility
chosen
Indicates that one entity is a sports facility where sports or physical activities can take place for the other entity.
- 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_69f76ed881408190bc62a969530a4a53 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69ff069ec1348190815375c5c9e38404 |
completed | May 9, 2026, 10:04 a.m. |
| PD | Predicate disambiguation | batch_69ff05ba57f88190a45d20f18044e0fb |
completed | May 9, 2026, 10 a.m. |
Created at: May 3, 2026, 4:18 p.m.