Triple
T5993149
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | New York Knicks–Brooklyn Nets rivalry |
E133399
|
entity |
| Predicate | fanbaseKnicks |
P897
|
FINISHED |
| Object | New York Knicks fans |
—
|
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: New York Knicks fans | Statement: [New York Knicks–Brooklyn Nets rivalry, fanbaseKnicks, New York Knicks fans]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: fanbaseKnicks Context triple: [New York Knicks–Brooklyn Nets rivalry, fanbaseKnicks, New York Knicks fans]
-
A.
KnicksCaptain
Indicates that the subject is the team captain of the New York Knicks.
-
B.
seriesOutcomeForKnicks
Indicates the result or outcome of a particular series as it pertains specifically to the New York Knicks.
-
C.
fanBase
chosen
Indicates that one entity is the group of admirers or supporters devoted to another entity.
-
D.
knicksRegularSeasonRecord
Indicates the relationship that specifies the New York Knicks’ win–loss record during a particular NBA regular season.
-
E.
yearsAsKnicksPresident
Indicates the number of years an individual has served in the role of president of the New York Knicks organization.
- 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_69c00870ddbc81909880fa3864f4f38d |
completed | March 22, 2026, 3:19 p.m. |
| NER | Named-entity recognition | batch_69c04e9189908190abc9c742b38dfabc |
completed | March 22, 2026, 8:18 p.m. |
| PD | Predicate disambiguation | batch_69c049e152e88190979ab80cb9b50321 |
completed | March 22, 2026, 7:58 p.m. |
Created at: March 22, 2026, 4:05 p.m.