Triple
T38535616
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | North Carolina vs. Michigan |
E923488
|
entity |
| Predicate | conferenceMichigan |
P3307
|
FINISHED |
| Object | Big Ten Conference |
—
|
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: Big Ten Conference | Statement: [North Carolina vs. Michigan, conferenceMichigan, Big Ten Conference]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: conferenceMichigan Context triple: [North Carolina vs. Michigan, conferenceMichigan, Big Ten Conference]
-
A.
conference
Indicates that an entity organizes, hosts, or is associated with a formal meeting or event where participants gather to discuss specific topics or share information.
-
B.
conference1
chosen
Indicates a relationship where an entity is associated with, participates in, or is characterized as a specific conference event or instance.
-
C.
conference2
Indicates that one entity is a conference or event that is associated with, hosted by, or otherwise related to another entity.
-
D.
otherConference
Indicates that one conference is distinct from and not the same as another conference.
-
E.
conferenceType
Indicates the specific category or kind of conference associated with an entity (e.g., workshop, symposium, seminar).
- 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_69f76ea8f6348190a5c03fb6292bbee3 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fd6dbd1b648190b1a0b391c03aebc5 |
completed | May 8, 2026, 4:59 a.m. |
| PD | Predicate disambiguation | batch_69fd6a9020548190bbfa845360ac85fb |
completed | May 8, 2026, 4:46 a.m. |
Created at: May 3, 2026, 4:32 p.m.