Triple
T29141166
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Michael Malone |
E738637
|
entity |
| Predicate | startedAsNBAAssistantCoach |
P196541
|
FINISHED |
| Object | New York Knicks |
E476
|
NE 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: New York Knicks | Statement: [Michael Malone, startedAsNBAAssistantCoach, New York Knicks]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: startedAsNBAAssistantCoach Context triple: [Michael Malone, startedAsNBAAssistantCoach, New York Knicks]
-
A.
numberOfNBATitlesAsAssistantCoach
Indicates the number of NBA championship titles an individual has won specifically in the role of an assistant coach.
-
B.
wonChampionshipAsAssistantCoachWith
Indicates that one entity served as an assistant coach on a team that won a championship together with the other entity.
-
C.
formerAssistantCoachAt
Indicates that a person previously held, but no longer holds, the position of assistant coach for a particular team or organization.
-
D.
beganHeadCoachingCareerWith
Indicates that an individual started their head coaching career with a specified team or organization.
-
E.
hasHeadCoachWithNBAExperience
Indicates that the entity’s head coach has prior coaching or playing experience in the NBA.
- F. None of above. chosen
Provenance (5 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_69f07cb3adb48190a9e0e169cd026634 |
completed | April 28, 2026, 9:24 a.m. |
| NER | Named-entity recognition | batch_69fe5c1a502081909d4024e514309c8e |
completed | May 8, 2026, 9:56 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a25505a8bcc81908e70d1ea8fe21d90 |
completed | June 7, 2026, 11:04 a.m. |
| PD | Predicate disambiguation | batch_69fe5a9df21c819087153f5d0bcaa987 |
completed | May 8, 2026, 9:50 p.m. |
| PDg | Predicate description generation | batch_69fe5c196f4081908f150d4cd6c528fa |
completed | May 8, 2026, 9:56 p.m. |
Created at: April 28, 2026, 11:36 a.m.