Triple
T4421997
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | NFL Kickoff Game |
E95121
|
entity |
| Predicate | scheduleContext |
P55062
|
FINISHED |
| Object | first regular-season game of the NFL season |
—
|
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: first regular-season game of the NFL season | Statement: [NFL Kickoff Game, scheduleContext, first regular-season game of the NFL season]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: scheduleContext Context triple: [NFL Kickoff Game, scheduleContext, first regular-season game of the NFL season]
-
A.
scheduleUS
Indicates that an entity arranges or assigns a time for something specifically within the context of the United States.
-
B.
schedule
Indicates that an entity arranges for an event, task, or activity to occur at a specific time or within a defined time frame.
-
C.
scheduledAs
chosen
Indicates that one entity is assigned or arranged to occur or function in the role, time, or capacity specified by another entity within a schedule.
-
D.
scheduleCount
Indicates the number of scheduled instances or events associated with a given entity or context.
-
E.
scheduledServiceType
Indicates the type or category of service that has been scheduled between entities (e.g., maintenance, appointment, or delivery).
- 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_69b3453a36908190b95a79a297ca083c |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b3554a0e7c8190b704d00d07b1857d |
completed | March 13, 2026, 12:07 a.m. |
| PD | Predicate disambiguation | batch_69b34f5eabe88190a12b244ea71e46d6 |
completed | March 12, 2026, 11:42 p.m. |
Created at: March 12, 2026, 11:30 p.m.