Triple
T29978485
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Miami Hurricanes athletics |
E761516
|
entity |
| Predicate | conferenceTitleLevel |
P180339
|
FINISHED |
| Object | ACC championships in multiple sports |
—
|
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: ACC championships in multiple sports | Statement: [Miami Hurricanes athletics, conferenceTitleLevel, ACC championships in multiple sports]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: conferenceTitleLevel Context triple: [Miami Hurricanes athletics, conferenceTitleLevel, ACC championships in multiple sports]
-
A.
conferenceLevel
Indicates the competitive or organizational tier at which a conference or event is classified or held.
-
B.
conferenceRank
Indicates the relative quality or prestige level assigned to a conference, typically used to rank it among other conferences.
-
C.
academicTitleLevel
Indicates the hierarchical rank or level associated with an entity’s academic title within an academic system.
-
D.
conferenceTitlesType
Indicates a relationship between conferences and the types or categories of titles associated with them.
-
E.
conferenceTitleCount
Indicates the number of distinct conference titles associated with a given entity or context.
- 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_69f2246851148190b8e76206db94b105 |
completed | April 29, 2026, 3:31 p.m. |
| NER | Named-entity recognition | batch_69f73ae120bc8190bff94d38d7a7a00d |
completed | May 3, 2026, 12:09 p.m. |
| PD | Predicate disambiguation | batch_69f73a38d0848190aa5139144b8561c6 |
completed | May 3, 2026, 12:06 p.m. |
| PDg | Predicate description generation | batch_69f73adfd9a081908adae6bd59dfefb9 |
completed | May 3, 2026, 12:09 p.m. |
Created at: April 29, 2026, 6:34 p.m.