Triple
T11620997
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | NFL Scouting Combine |
E275635
|
entity |
| Predicate | timingRelativeToEvent |
P35710
|
FINISHED |
| Object | held before the NFL Draft |
—
|
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: held before the NFL Draft | Statement: [NFL Scouting Combine, timingRelativeToEvent, held before the NFL Draft]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: timingRelativeToEvent Context triple: [NFL Scouting Combine, timingRelativeToEvent, held before the NFL Draft]
-
A.
timingParameter
Indicates a relationship where one entity specifies or controls a temporal setting, constraint, or configuration parameter that determines the timing behavior of another entity or process.
-
B.
timingMethod
Indicates the method or technique used to measure or record the timing of an event or process.
-
C.
timeCorrelation
Indicates that two events or states are related in time such that changes or occurrences in one are systematically associated with changes or occurrences in the other.
-
D.
timePeriodEvent
chosen
Indicates that an event occurs, is scheduled, or is valid within a specified time period.
-
E.
timeBehind
Indicates that one entity occurs or is positioned later in time than another, lagging behind it on a temporal scale.
- 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_69d6aaf84b548190ac072e4fb89ae18f |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d8a1206f1c81908d92024ef71958c0 |
completed | April 10, 2026, 7:05 a.m. |
| PD | Predicate disambiguation | batch_69d85dd6503c819081f9045e9d5c4f3f |
completed | April 10, 2026, 2:17 a.m. |
Created at: April 8, 2026, 9:39 p.m.