Triple
T35251849
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Super Bowl LVII halftime show |
E1018114
|
entity |
| Predicate | previousSponsorReplaced |
P96865
|
FINISHED |
| Object | Pepsi |
—
|
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: Pepsi | Statement: [Super Bowl LVII halftime show, previousSponsorReplaced, Pepsi]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: previousSponsorReplaced Context triple: [Super Bowl LVII halftime show, previousSponsorReplaced, Pepsi]
-
A.
previousSponsor
Indicates that an entity formerly acted as a sponsor for another entity at some earlier time but no longer does so.
-
B.
previousSponsorshipName
Indicates that an entity had a different sponsorship name in the past, specifying what that prior sponsored name was.
-
C.
formerSponsor
Indicates that an entity previously acted as a sponsor for another entity but no longer holds that sponsoring role.
-
D.
sponsorshipChangeFromPredecessor
Indicates that the sponsorship of an entity has been altered from that provided by its predecessor entity.
-
E.
sponsorshipChangeTo
chosen
Indicates a change in sponsorship where an entity becomes the new sponsor of another entity, replacing or updating the previous sponsorship arrangement.
- 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_69f76de407d081909dfc3c419817ae93 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69ff5b233e9c8190adc06cca0758986b |
completed | May 9, 2026, 4:04 p.m. |
| PD | Predicate disambiguation | batch_69ff5a5682108190a006b23c4fcdcc7c |
completed | May 9, 2026, 4:01 p.m. |
Created at: May 3, 2026, 4:02 p.m.