Triple
T32614822
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | AHL scoring champion trophy |
E833754
|
entity |
| Predicate | pointsDefinition |
P17093
|
FINISHED |
| Object | goals plus assists |
—
|
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: goals plus assists | Statement: [AHL scoring champion trophy, pointsDefinition, goals plus assists]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: pointsDefinition Context triple: [AHL scoring champion trophy, pointsDefinition, goals plus assists]
-
A.
pointDefinition
chosen
Indicates that one entity serves as the defining description or specification of a particular point in another entity.
-
B.
points
Indicates that one entity directs attention, focus, or a physical/abstract indication toward another entity or location.
-
C.
pointsSource
Indicates that one entity serves as the origin or source from which points (such as scores, credits, or coordinates) are derived or assigned to another entity.
-
D.
positions
Indicates that one entity assigns, arranges, or places another entity in a specific location, role, or order relative to others.
-
E.
leafPoints
Indicates that one leaf or leaf-like structure is oriented or directed toward, or points at, another entity.
- 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_69f3492bfa648190b6ae472074634e29 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69f6c8159edc8190b1c87015e0c820e8 |
completed | May 3, 2026, 3:59 a.m. |
| PD | Predicate disambiguation | batch_69f6c3f42fbc8190a06eb1044c9e6094 |
completed | May 3, 2026, 3:41 a.m. |
Created at: May 1, 2026, 1:06 a.m.