Triple
T10864228
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Florida–Georgia football game |
E256485
|
entity |
| Predicate | stadiumSeatingSplit |
P96130
|
FINISHED |
| Object | approximately 50–50 between Florida and Georgia fans |
—
|
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: approximately 50–50 between Florida and Georgia fans | Statement: [Florida–Georgia football game, stadiumSeatingSplit, approximately 50–50 between Florida and Georgia fans]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: stadiumSeatingSplit Context triple: [Florida–Georgia football game, stadiumSeatingSplit, approximately 50–50 between Florida and Georgia fans]
-
A.
hasSeatingSections
Indicates that an entity is divided into distinct seating areas or sections designated for occupants.
-
B.
seatsPerRow
Indicates the number of seats that are arranged in each row within a seating layout or configuration.
-
C.
individualSeats
Indicates that an entity provides or consists of separate, single-person seating positions rather than shared or bench-style seating.
-
D.
numberOfSeatingRows
Indicates the total count of seating rows associated with an entity, such as a venue, vehicle, or seating area.
-
E.
seatCategory
Indicates the classification or type of a seat (e.g., by comfort level, price tier, or section) assigned to an entity.
- 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_69d6aa83d1448190a66d93c32394d21f |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d7516b2f148190adbacd35fc8c2056 |
completed | April 9, 2026, 7:12 a.m. |
| PD | Predicate disambiguation | batch_69d70d308dfc81908792f98cfb871392 |
completed | April 9, 2026, 2:21 a.m. |
| PDg | Predicate description generation | batch_69d7101c96708190808fef73199e8482 |
completed | April 9, 2026, 2:34 a.m. |
Created at: April 8, 2026, 9:20 p.m.