Triple
T8410123
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2018 NBA All-Star Game |
E198600
|
entity |
| Predicate | isFirstToUseFormat |
P6318
|
FINISHED |
| Object | draft-style captain format |
—
|
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: draft-style captain format | Statement: [2018 NBA All-Star Game, isFirstToUseFormat, draft-style captain format]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isFirstToUseFormat Context triple: [2018 NBA All-Star Game, isFirstToUseFormat, draft-style captain format]
-
A.
firstUsedFor
chosen
Indicates that one entity was the earliest or original thing for which another entity was used or applied.
-
B.
firstMajorReleaseUsingFormat
Indicates that the subject is the first major release to use a particular format.
-
C.
firstCreatedUsing
Indicates that one entity was initially produced or brought into existence through the use, application, or involvement of another entity.
-
D.
firstReleaseFormat
Indicates the original medium or format in which something (such as a work or product) was first released.
-
E.
wasFirst
Indicates that one entity occurred, appeared, or held a position before another in time or sequence.
- 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_69ca831201b481909e137936ef99ff11 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cb83dec1f08190ae08719e860b29fa |
completed | March 31, 2026, 8:20 a.m. |
| PD | Predicate disambiguation | batch_69cb70d473dc8190af8ea81ee5aa970d |
completed | March 31, 2026, 6:59 a.m. |
Created at: March 30, 2026, 6:05 p.m.