Triple
T4859134
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jason Spezza |
E108610
|
entity |
| Predicate | formedLine |
P59425
|
FINISHED |
| Object | "Pizza Line" with Dany Heatley and Daniel Alfredsson |
—
|
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: "Pizza Line" with Dany Heatley and Daniel Alfredsson | Statement: [Jason Spezza, formedLine, "Pizza Line" with Dany Heatley and Daniel Alfredsson]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: formedLine Context triple: [Jason Spezza, formedLine, "Pizza Line" with Dany Heatley and Daniel Alfredsson]
-
A.
formerLine
Indicates that an entity previously served as a particular transit or service line but no longer does so.
-
B.
formsPartOfLine
Indicates that one element constitutes a segment or component belonging to a larger line.
-
C.
connectedLine
Indicates that two entities are joined by a continuous line or linear connection.
-
D.
associatedLine
Indicates that one entity is linked or connected to a particular line (such as a line item, line of text, or line in a structure) with which it is contextually or functionally related.
-
E.
isLinedWith
Indicates that one object or surface is covered, edged, or internally coated along its length or area with another material or layer.
- 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_69bd440b965081908b0557721cae6338 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd6d5c92148190a314707bdd3ff30f |
completed | March 20, 2026, 3:53 p.m. |
| PD | Predicate disambiguation | batch_69bd6c27334481909ba8ac80854f7d8e |
completed | March 20, 2026, 3:47 p.m. |
| PDg | Predicate description generation | batch_69bd6cfa8bd881908e376ab286759cc2 |
completed | March 20, 2026, 3:51 p.m. |
Created at: March 20, 2026, 1:26 p.m.