Triple
T33941485
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Beijing Royal Fighters |
E870177
|
entity |
| Predicate | formerNBAPlayerAsCoach |
P201311
|
FINISHED |
| Object | Stephon Marbury |
—
|
NE NERFINISHED |
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: Stephon Marbury | Statement: [Beijing Royal Fighters, formerNBAPlayerAsCoach, Stephon Marbury]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: formerNBAPlayerAsCoach Context triple: [Beijing Royal Fighters, formerNBAPlayerAsCoach, Stephon Marbury]
-
A.
former coach
Indicates that one entity previously served as the coach of another entity but no longer holds that position.
-
B.
NBAteamCoached
Indicates that one entity is a coach who has coached the other entity, which is an NBA team.
-
C.
hasHeadCoachWithNBAExperience
Indicates that the entity’s head coach has prior coaching or playing experience in the NBA.
-
D.
NBAHeadCoachingDebutTeam
Indicates the team for which a person made their debut as a head coach in the NBA.
-
E.
NBAHeadCoachDebutSeason
Indicates the season in which a person first served as a head coach for an NBA 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_69f3499b0dd48190b07b4b60babcee02 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69ffe8ebe9fc8190b1934a3c4074370c |
completed | May 10, 2026, 2:09 a.m. |
| PD | Predicate disambiguation | batch_69ffe83a5de88190bed3e8bac86e8760 |
completed | May 10, 2026, 2:06 a.m. |
| PDg | Predicate description generation | batch_69ffe8eb47d48190acf7794ebe3ef4b8 |
completed | May 10, 2026, 2:09 a.m. |
Created at: May 1, 2026, 1:49 a.m.