Triple
T10425361
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Martin St. Louis |
E245770
|
entity |
| Predicate | coachingStartWithMontrealCanadiens |
P17026
|
FINISHED |
| Object | 2022 |
—
|
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: 2022 | Statement: [Martin St. Louis, coachingStartWithMontrealCanadiens, 2022]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: coachingStartWithMontrealCanadiens Context triple: [Martin St. Louis, coachingStartWithMontrealCanadiens, 2022]
-
A.
coachingStart
chosen
Indicates the point in time when a coaching relationship or coaching session begins.
-
B.
beganCoachingInOHL
Indicates the time or context in which a person started their coaching role in the Ontario Hockey League (OHL).
-
C.
MontrealTeamCurrentName
Indicates that the current official name of a Montreal-based team is being specified or associated with that team.
-
D.
coachedStanleyCupFinalist
Indicates that a person served as the coach of a team that reached the Stanley Cup Final.
-
E.
beganUnderCoach
Indicates that one entity started its activity, career, or involvement while being coached or supervised by 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_69d381bf3dc08190bf35a2643e4e8f22 |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4ea48cb348190ad4432f263300592 |
completed | April 7, 2026, 11:28 a.m. |
| PD | Predicate disambiguation | batch_69d4dfb9d3648190aaabed901f22a8c0 |
completed | April 7, 2026, 10:43 a.m. |
Created at: April 6, 2026, 12:12 p.m.