Triple

T28750152
Position Surface form Disambiguated ID Type / Status
Subject Team Stephen E731498 entity
Predicate draftMethod P165281 FINISHED
Object player draft by team captain 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: player draft by team captain | Statement: [Team Stephen, draftMethod, player draft by team captain]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: draftMethod
Context triple: [Team Stephen, draftMethod, player draft by team captain]
  • A. draft_m
    Indicates that an entity is involved in creating, editing, or preparing a preliminary or non-final version of another entity.
  • B. draftSystem
    Indicates a system or mechanism responsible for selecting, assigning, or organizing individuals for compulsory service, typically in a military or similar structured context.
  • C. draft
    Indicates that one entity prepares an initial or preliminary version of something, typically a document, plan, or design, which may be revised later.
  • D. draftApprox
    Indicates an approximate or provisional drafting relationship, where one entity serves as a non-final or estimated draft version of another.
  • E. draftType
    Indicates the specific category or kind of draft associated with an entity or document (e.g., initial, revised, or final draft).
  • 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_69f043ecb5c081909ec9da1172d68ece completed April 28, 2026, 5:21 a.m.
NER Named-entity recognition batch_69f657bd25b88190bdded04512eddaef completed May 2, 2026, 7:59 p.m.
PD Predicate disambiguation batch_69f651ada6048190a7b4a6981565dc3a completed May 2, 2026, 7:34 p.m.
PDg Predicate description generation batch_69f6562ef4e4819082ce6abd41b74dc5 completed May 2, 2026, 7:53 p.m.
Created at: April 28, 2026, 6:07 a.m.