Triple
T10002174
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John B. Sollenberger Trophy |
E197352
|
entity |
| Predicate | pointComponents |
P70318
|
FINISHED |
| Object | goals and 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 and assists | Statement: [John B. Sollenberger Trophy, pointComponents, goals and assists]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: pointComponents Context triple: [John B. Sollenberger Trophy, pointComponents, goals and assists]
-
A.
pointDefinition
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.
leafPoints
Indicates that one leaf or leaf-like structure is oriented or directed toward, or points at, another entity.
-
D.
formationComponents
chosen
Indicates that one entity is composed of, or structurally includes, the other entities as its constituent parts or components.
-
E.
componentPosition
Indicates the spatial or logical placement of a component relative to a larger structure or system.
- 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_69ca82f3b61c81908ecc2c1c96dbc2e4 |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cdcc9078788190a4e75dd7ff830c63 |
completed | April 2, 2026, 1:55 a.m. |
| PD | Predicate disambiguation | batch_69cd1da2cf9081908a6c0eb5247d0bc2 |
completed | April 1, 2026, 1:29 p.m. |
Created at: March 30, 2026, 8:51 p.m.