Triple
T6862721
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Craig McRae |
E158320
|
entity |
| Predicate | startTime_coachOf_Collingwood Football Club |
P74170
|
FINISHED |
| Object | 2021 |
—
|
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: 2021 | Statement: [Craig McRae, startTime_coachOf_Collingwood Football Club, 2021]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: startTime_coachOf_Collingwood Football Club Context triple: [Craig McRae, startTime_coachOf_Collingwood Football Club, 2021]
-
A.
AFLCoach
Indicates that one entity serves as the head coach of an Australian Football League (AFL) team represented by the other entity.
-
B.
gamesCoachedWithTeam
Indicates the number of games a coach has led while associated with a specific team.
-
C.
teamCoachedFrom
Indicates that a coaching relationship exists where a coach is responsible for training or managing a team originating from a specific organization, location, or context.
-
D.
workedUnderHeadCoach
Indicates that one person held a role or position under the authority or supervision of another person who was serving as the head coach.
-
E.
coachOf
Indicates that one entity serves as the coach (trainer or manager) of another entity, typically a person or team.
- 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_69c68830cdbc8190a8301c7a9d9f651a |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6da3ce95081909a424ac04bc7fa07 |
completed | March 27, 2026, 7:27 p.m. |
| PD | Predicate disambiguation | batch_69c6d7b168908190b2f7c724b1bc7fc9 |
completed | March 27, 2026, 7:17 p.m. |
| PDg | Predicate description generation | batch_69c6da3b5510819093c5893ea92ac025 |
completed | March 27, 2026, 7:27 p.m. |
Created at: March 27, 2026, 2:21 p.m.