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.