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.