Triple
T27119720
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | NLL Entry Draft |
E686961
|
entity |
| Predicate | draftOrderBasis |
P76535
|
FINISHED |
| Object | previous season standings |
—
|
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: previous season standings | Statement: [NLL Entry Draft, draftOrderBasis, previous season standings]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: draftOrderBasis Context triple: [NLL Entry Draft, draftOrderBasis, previous season standings]
-
A.
draftType
Indicates the specific category or kind of draft associated with an entity or document (e.g., initial, revised, or final draft).
-
B.
draftApprox
Indicates an approximate or provisional drafting relationship, where one entity serves as a non-final or estimated draft version of another.
-
C.
orderDefinitionBasedOn
Indicates that one item’s definition or specification is arranged, derived, or structured based on the definition or specification of another item.
-
D.
assignmentBasis
chosen
Indicates the criterion or rationale on which an assignment or allocation is determined.
-
E.
draftOrSigning
Indicates a relationship where an entity is involved in either the drafting or the signing phase of a document, agreement, or formal instrument.
- 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_69ef148c2b588190afc15b529f7af845 |
completed | April 27, 2026, 7:47 a.m. |
| NER | Named-entity recognition | batch_69f624421d188190a5356a4596df536e |
completed | May 2, 2026, 4:20 p.m. |
| PD | Predicate disambiguation | batch_69f61b40f02081909bd9c3ea73249163 |
completed | May 2, 2026, 3:41 p.m. |
Created at: April 27, 2026, 8:58 a.m.