Triple
T695251
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Peter Šťastný |
E13880
|
entity |
| Predicate | draftStatus |
P17567
|
FINISHED |
| Object | undrafted in NHL |
—
|
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: undrafted in NHL | Statement: [Peter Šťastný, draftStatus, undrafted in NHL]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: draftStatus Context triple: [Peter Šťastný, draftStatus, undrafted in NHL]
-
A.
draft
Indicates that one entity prepares an initial or preliminary version of something, typically a document, plan, or design, which may be revised later.
-
B.
hasDraft
Indicates that one entity possesses or is associated with a preliminary or unfinished version of another entity.
-
C.
draftingStarted
Indicates that the process of creating an initial version or draft of something has begun.
-
D.
draftType
Indicates the specific category or kind of draft associated with an entity or document (e.g., initial, revised, or final draft).
-
E.
draftSystem
Indicates a system or mechanism responsible for selecting, assigning, or organizing individuals for compulsory service, typically in a military or similar structured context.
- 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_69a493406c408190957eeec9048a8fb6 |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a4a0c3f39c8190a3014df428817492 |
completed | March 1, 2026, 8:25 p.m. |
| PD | Predicate disambiguation | batch_69a49d23e0a08190b08be9d1eff2a1bb |
completed | March 1, 2026, 8:10 p.m. |
| PDg | Predicate description generation | batch_69a49df19c9481909cc9bc33ed7f011b |
completed | March 1, 2026, 8:13 p.m. |
Created at: March 1, 2026, 7:36 p.m.