Triple
T14074809
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Beast Quake run vs New Orleans Saints |
E338703
|
entity |
| Predicate | startingFieldPosition |
P77379
|
FINISHED |
| Object | Seattle 33-yard line |
—
|
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: Seattle 33-yard line | Statement: [Beast Quake run vs New Orleans Saints, startingFieldPosition, Seattle 33-yard line]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: startingFieldPosition Context triple: [Beast Quake run vs New Orleans Saints, startingFieldPosition, Seattle 33-yard line]
-
A.
initiatingPosition
chosen
Indicates the starting location or initial spatial position from which an action, process, or movement begins.
-
B.
positionInField
Indicates the specific role, location, or functional placement an entity occupies within a defined field, domain, or area of activity.
-
C.
playingPosition
Indicates the specific role or position an individual occupies while participating in a game or sport.
-
D.
startingZoneFor
Indicates the zone or area where an entity initially begins, is placed, or starts its activity or process.
-
E.
relativePositionInStadium
Indicates the spatial relationship between entities based on where they are located relative to each other within a stadium.
- 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_69d81c687b0c819087fd9ed4198403f8 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de5c5bc49881909012b66fa451f495 |
completed | April 14, 2026, 3:25 p.m. |
| PD | Predicate disambiguation | batch_69de05b0e6c88190a819eeba0028981f |
completed | April 14, 2026, 9:15 a.m. |
Created at: April 9, 2026, 10:21 p.m.